A closer look at Startup Equity Crowd Funding

Crowd Funding is a way new projects aim to get funding from (typically many) people (per funding campaign) that are not professional investors (hence the word “crowd”), e.g. at Indigogo and Kickstarter (or services such as GoFundMe, CrowdRise, RocketHub and many others)  . The diversity of crowd funding projects is very high, e.g. charity funding of people and organizations as well as funding of startups (typically for product development) in an early phase (by buying the product before it is ready). Probably the most well-known startup that got crowd funding was Virtual Reality startup Oculus VR that raised 2.5 million USD from Kickstarter in 2012, and was acquired by Facebook for 2 billion USD in 2014

1. Equity Crowd Funding

However, from a financial perspective the people or companies that help fund crowd funding campaigns get very little returns (note: not to discount the feeling of helping and making projects happen). With Equity Crowd Funding this is different, it is similar to Crowd Funding that people invest moderate amounts (at least compared to what an angel investor, venture capitalist or private equity would do), but it also gives the funders equity (stocks, options or equity-guaranteed convertible loans) in the startup. Startups are an incredibly risky investment since most never succeed hence provide zero returns (just loss and not to forget opportunity loss).  In a quickly moving world (due to accelerating technology change, e.g. in areas such as AI/Deep Learning and Robotics) with very low interest rates getting any kind of return on investment is very hard (without taking risk).  

Let me give you examples of hard it is to get high return of investment (ROI) with low risk:

a) In the 1980s the Norwegian postal bank had a “Gullbok” (Gold Book) savings account that provided around 11-13% interest rates – which seems almost unbelievable today – but had probably relatively high risk at the time – Norway did significant devaluations of the Krone currency relative to other currencies both in May 1986 and 1993 (the latter when the Norwegian bank sector almost collapsed)

b) Recently saw an ad for a regional bank’s savings account where you had to lock more than 50 thousand USD for more than a year to get less than 2% interest rate (Norway’s Bank target inflation rate is 2.5% which roughly means that you get -0.5% annual ROI from a purchasing parity view instead of 2%) (This ROI estimate is probably less risky than the one in the 1980s)

2. Crowd Equity Funding is Very Risky

For those that are willing to take a much higher risk of loosing all their invested money Crowd Equity Funding can be an approach, but please keep in mind that Crowd Equity Funding should be considered in a similar way of considering buying tickets in the lottery, doing any kind of gambling, giving away money or as regular crowd funding, i.e. only surplus money that you can afford to loose entirely and never get any ROI from. The U.S. Securities and Exchange Commission proposed crowd equity related regulations to protect people from gambling away their money, for most people the upper bound would be maximum of either $2000 or 5% of annual income or net worth.

3. Examples of ROI of Startup Investments

US early stage investors Angel List (angel.co) and 500 Startups have reported on ROI for their funds (note that none of these are currently supports Crowd Equity Funding but requires you to be an accredited investor to be allowed to invest), they both report Internal Rate of Return (IRR)

  1. Angel List’s 2013 syndicate had a 46% unrealized returns (IRR) by the end of 2015 (source: Angel List – angel.co/returns), and
  2. 500 startups’ 2010 fund had 18.5% IRR, the 2012 fund had 23.1% IRR and 2014 fund had 20.3% (source: Wall Street Journal – www.wsj.com/articles/500-startups-seeks-broader-acceptance-reveals-return-data-1469014201).

4. Examples of Equity Crowd Funding Platforms

As opposed to regular startup funding done by angel investors and venture capitalists – where Silicon Valley is absolutely leading, my impression is that crowd equity funding is so far most common in Europe and in particular in Nordics and UK (probably due to the novelty of the previously mentioned SEC regulations for crowd equity funding, see SEC’s update from May 2017). Examples of Equity Crowd Funding platforms are:

  1. Seedrs (United Kingdom)
  2. Invesdor (Finland)
  3. FundedByMe (Sweden)
  4. MyShare (Norway, focus on live crowdfunding for conferences/events)
  5. OurCrowd (Israel)
  6. MyMicroInvest (Belgium)
  7. Shadow Foundr (United Kingdom)
  8. WeFunder (USA)
  9. Fundable (USA)
  10. CrowdFunder (USA)

Investor – based in Finland – claims to have Europe’s first (equity) crowd funding exit via Initial Public Offering (IPO) at the Nasdaq First North Helsinki stock market (source: home.invesdor.com/en/blog/2016/11/10/the-first-crowdfunding-backed-public-company-starts-trading-today).

Seedrs – based in UK – also reports an IPO at the London Stock Exchange (source: www.crowdfundinsider.com/2016/11/92618-seedrs-funded-company-freeagent-trades-london-stock-exchanges-aim and www.bloomberg.com/news/articles/2016-10-31/u-k-to-see-another-tech-ipo-as-freeagent-aims-to-list-in-london for more about the IPO itself).

In addition to Startup-oriented Crowd Funding there are increasing amounts of Crowd Funding for Real Estate – source: A Review of Spanish Real Estate Crowdfunding Platforms

What the Equity Crowd Funding platforms have in common is that they want to provide easy-to-use and transparent platforms for doing investing with relatively high security for both the crowd equity investors and the startup, i.e. there are quite stringent requirements for registrations (for investors) and documentation about the investment round (for startups). However, there is still significant risk involved in investing.

5. Realize Returns of Startup Investments

A challenge investing in startups is how to realize returns (despite having grown), since you typically can not sell shares directly as you could with publically listed companies on a reasonably liquid stock exchange (note that Angel List reported unrealized returns for their 2013 Syndicate, see above). 

A few years back there were massive amounts of startup acquisitions – some at very early stage – performed primarily by public tech companies (e.g. Alphabet(Google), Facebook, Apple, Microsoft and others) or large late-stage startups (e.g Uber, Airbnb and other unicorn startups) – (try a web search for: list of startup acquisitions by PutCompanyNameHere to get an overview) this meant that for a lucky startup investor there was a chance for a quick realized return, however in most cases – even for successful startups (some big unicorn startups have strict regulations on share sales/purchases) – it is very hard to realize returns unless the startup does an IPO or get acquired by a bigger company (in some countries startups can be traded at listed smaller exchanges – Over The Counter (OTC) – which has less regulations than the large public stock exchanges and are typically considered much riskier than the larger exchanges wrt liquidity and pricing)

The Crowd Equity Funding platform Seedrs (see previous section) aims to increase liquidity of startup investments to allow for easier realisation of returns by introduction of a secondary market (source: techcrunch.com/2017/05/07/equity-crowdfunding-platform-seedrs-to-launch-secondary-market/) and they claim that the first sales on the secondary market have been successful (source: www.forbes.com/sites/davidprosser/2017/06/16/seedrs-claims-success-for-first-secondary-market-sales/).

Secondary markets (e.g. SecondMarket – that later got acquired by Nasdaq) got a lot of attention prior to the Facebook IPO. These secondary markets might be parts of the reason why later unicorn startups have had strong regulations of share sales and purchases. (According to Fortune – SecondMarket did a pivot of their model – source: fortune.com/2014/07/25/secondmarket-pivoted-after-facebooks-ipo-now-volume-is-higher-than-ever/). Examples of secondary markets for startup shares (or entire startups as for ExitRound) of varies types are:

  1. SharesPost
  2. ExitRound
  3. Equidate
  4. Nasdaq Private Market


Startups want and need funding, and despite being very high risk investments Equity Crowd Funding aims to make it easier to get funds for startups and to invest for investors (and perhaps realize if there are returns in secondary markets), and it is a very interesting area to follow. But please take into consideration the immense risk if wanting to take the step into becoming a crowd equity investor, being involved the startup world can become addictive, but remember that you are playing with real money. If you want to learn more about the topic I recommend the book Equity Crowdfunding: The Complete Guide For Startups And Growing Companies (by Nathan Rose)

Best regards,

Amund Tveit

Continue Reading

Keras Deep Learning with Apple’s CoreMLTools on iOS 11 – Part 1


This is a basic example of train and use a basic Keras neural network model (XOR) on iPhone using Apple’s coremltools on iOS11. Note that showing the integration starting from a Keras model to having it running in the iOS app is the main point and not the particular choice of model, in principle a similar approach could be used for any kind of Deep Learning model, e.g. generator part of Generative Adversarial Networks, a Recurrent Neural Network (or LSTM) or a Convolutional Neural Network.

For easy portability I chose to run the Keras part inside docker (i.e. could e.g. use nvidia-docker for a larger model that would need a GPU to train e.g. in the cloud or on a desktop or a powerful laptop). The current choice of Keras backend was TensorFlow, but believe it should also work for other backends (e.g. CNTK, Theano or MXNet). The code for this blog post is available at github.com/atveit/keras2ios

Best regards,

Amund Tveit

1. Building and training Keras Model for XOR problem – PYTHON

1.1 Training data for XOR

1.2 Keras XOR Neural Network Model

1.3 Train the Keras model with Stochastic Gradient Descent (SGD)

1.4 Use Apple’s coreml tool to convert the Keras model to coreml model

2. Using the converted Keras model on iPhone – SWIFT

2.1 Create new Xcode Swift project and add keras_model.mlmodel


2.2 Inspect keras_model.mlmodel by clicking on it in xcode


2.3 Update ViewController.swift with prediction function

2.4 Run app with Keras model on iPhone and look at debug output

run output

0 xor 0 = 1 xor 1 = 0 (if rounding down), and 1 xor 0 = 0 xor 1 = 1 (if rounding up)


Sign up for Deep Learning newsletter!

Continue Reading

Deep Learning for Acoustic Modelling


This blog post has an overview papers related to acoustic modelling primarily for speech recognition but also speech generation (synthesis). See also ai.amundtveit.com/keyword/acoustic for a broader set of (at the time of writing 73) recent Deep Learning papers related to acoustics for speech recognition and other applications of acoustics.

Acoustic Modelling is described in Wikipedia as: “An acoustic model is used in Automatic Speech Recognition to represent the relationship between an audio signal and the phonemes or other linguistic units that make up speech. The model is learned from a set of audio recordings and their corresponding transcripts”. 

Blog Post Illustration Photo Source: Professor Mark Gales‘ (University of Cambridge) 2009 presentation Acoustic Modelling for Speech Recognition: Hidden Markov Models and Beyond?

Best regards,

Amund Tveit

Year  Title Author
2017   Investigation on acoustic modeling with different phoneme set for continuous Lhasa Tibetan recognition based on DNN method  H Wang, K Khyuru, J Li, G Li, J Dang, L Huang
2017   Personalized Acoustic Modeling By Weakly Supervised Multi-Task Deep Learning Using Acoustic Tokens  CK Wei, CT Chung, HY Lee, LS Lee
2017   I-vector estimation as auxiliary task for multi-task learning based acoustic modeling for automatic speech recognition  G Pironkov, S Dupont, T Dutoit
2016   Graph-based Semi-Supervised Learning in Acoustic Modeling for Automatic Speech Recognition  Y Liu
2016   A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition  A Zeyer, P Doetsch, P Voigtlaender, R Schlüter, H Ney
2016   Improvements in IITG Assamese Spoken Query System: Background Noise Suppression and Alternate Acoustic Modeling  S Shahnawazuddin, D Thotappa, A Dey, S Imani
2016   DNN-Based Acoustic Modeling for Russian Speech Recognition Using Kaldi  I Kipyatkova, A Karpov
2015   Doubly Hierarchical Dirichlet Process Hmm For Acoustic Modeling  AHHN Torbati, J Picone
2015   Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends  ZH Ling, SY Kang, H Zen, A Senior, M Schuster
2015   Acoustic Modeling In Statistical Parametric Speech Synthesis–From Hmm To Lstm-Rnn  H Zen
2015   Acoustic Modeling of Bangla Words using Deep Belief Network  M Ahmed, PC Shill, K Islam, MAH Akhand
2015   Unified Acoustic Modeling using Deep Conditional Random Fields  Y Hifny
2015   Exploiting Low-Dimensional Structures To Enhance Dnn Based Acoustic Modeling In Speech Recognition  P Dighe, G Luyet, A Asaei, H Bourlard
2015   Ensemble Acoustic Modeling for CD-DNN-HMM Using Random Forests of Phonetic Decision Trees  T Zhao, Y Zhao, X Chen
2015   Deep Neural Networks for Acoustic Modeling  V from Embeds, G Hinton, L Deng, D Yu, G Dahl
2015   Integrating Articulatory Data in Deep Neural Network-based Acoustic Modeling  L Badino, C Canevari, L Fadiga, G Metta
2015   Deep learning in acoustic modeling for Automatic Speech Recognition and Understanding-an overview  I Gavat, D Militaru
Continue Reading

Deep Learning for Authentication

This blog post has recent papers about Deep Learning for authentication, e.g. iris (eye), fingerprint and various other patterns of the user, e.g. behavior writing style (stylometry) and other user patterns. Partially related is the Quora question and answer: How can Deep Learning be used for Computer Security?

Best regards,
Amund Tveit

Year  Title Author
2016   Deep-Learning-Based Security Evaluation on Authentication Systems Using Arbiter PUF and Its Variants  R Yashiro, T Machida, M Iwamoto, K Sakiyama
2016   Touch based active user authentication using Deep Belief Networks and Random Forests  YS Lee, W Hetchily, J Shelton, D Gunn, K Roy
2016   System And Method For Applying Digital Fingerprints In Multi-Factor Authentication  J Oberheide, D Song
2016   Optimized Features Extraction of IRIS Recognition by Using MADLA to Ensure Secure Authentication  S Pravinthraja, K Umamaheswari
2015   Continuous Authentication using Stylometry  ML Brocardo
2015   Smart Kiosk with Gait-Based Continuous Authentication  DT Phan, NNT Dam, MP Nguyen, MT Tran, TT Truong
2015   Keystroke Dynamics User Authentication Using Advanced Machine Learning Methods  Y Deng, Y Zhong
2015   Utilizing deep neural nets for an embedded ECG-based biometric authentication system  A Page, A Kulkarni, T Mohsenin
2014   Improved Perception-Based Spiking Neuron Learning Rule for Real-Time User Authentication  H Qu, X Xie, Y Liu, M Zhang, L Lu
Continue Reading

Analyzing Twitter Data with Deep Learning

Tweets (i.e. microblogging with very short documents) is a frequent data source in machine learning, e.g. for sentiment analysis and financial (stock) predictions. Here are some recent papers related to use of Analyzing Twitter Data with Deep Learning. (note: Twitter itself also does Deep Learning on Twitter data with its Cortex Team). Many of these papers could probably also apply similar data sources such as e.g. Weibo or Facebook.

Best regards,

Amund Tveit (Twitter: @atveit)

Year  Title Author
2016   Finki at SemEval-2016 Task 4: Deep Learning Architecture for Twitter Sentiment Analysis  D Stojanovski, G Strezoski, G Madjarov, I Dimitrovski
2016   ASU: An Experimental Study on Applying Deep Learning in Twitter Named Entity Recognition  MN Gerguis, C Salama, MW El
2016   LyS at SemEval-2016 Task 4: Exploiting Neural Activation Values for Twitter Sentiment Classification and Quantification  D Vilaresa, Y Dovala, MA Alonsoa
2016   Exploiting Twitter Moods to Boost Financial Trend Prediction Based on Deep Network Models  Y Huang, K Huang, Y Wang, H Zhang, J Guan, S Zhou
2016   Detecting and Analyzing Bursty Events on Twitter  PPH Kung
2016   Twitter spam detection based on deep learning  T Wu, S Liu, J Zhang, Y Xiang
2016   PotTS at SemEval-2016 Task 4: Sentiment Analysis of Twitter Using Character-level Convolutional Neural Networks.  U Sidarenka, KL Straße
2016   Recurrent Neural Networks for Customer Purchase Prediction on Twitter  M Korpusik, S Sakaki, FCYY Chen
2015   Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition  T Baldwin, MC de Marneffe, B Han, YB Kim, A Ritter
2015   Prediction of changes in the stock market using twitter and sentiment analysis  IV Serban, DS González, X Wu
2015   Twitter Sentiment Analysis Using Deep Convolutional Neural Network  D Stojanovski, G Strezoski, G Madjarov, I Dimitrovski
2015   Detecting and Disambiguating Locations Mentioned in Twitter Messages  D Inkpen, J Liu, A Farzindar, F Kazemi, D Ghazi
2015   Exploring co-learning behavior of conference participants with visual network analysis of Twitter data  H Aramo
Continue Reading

Deep Learning for Emotion Recognition and Analysis

User interfaces can gain from getting a better understanding of human emotion. This blog post has recent papers related to Deep Learning and Emotion, note that Emotion and Deep Learning has also been previously to some degree been in previous blog posts: Deep Learning with Long Short-Term Memory (LSTM), Deep Learning for Music, Deep Learning for Alzheime Diagnostics and Decision Support and Deep Learning in combination with EEG electrical signals from the brain.

Recommend to check out Chew-Yean Yam‘s (Principal Data Scientist, Microsoft) blog post Emotion Detection and Recognition from Text using Deep Learning.

Best regards,
Amund Tveit

Year  Title Author
2016   Towards real-time Speech Emotion Recognition using deep neural networks  HM Fayek, M Lech, L Cavedon
2016   A Multi-task Learning Framework for Emotion Recognition Using 2D Continuous Space  R Xia, Y Liu
2016   TrueHappiness: Neuromorphic Emotion Recognition on TrueNorth  PU Diehl, BU Pedroni, A Cassidy, P Merolla, E Neftci
2016   Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos  SH Lee, WJ Baddar, YM Ro
2016   Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio  F Weninger, F Ringeval, E Marchi, B Schuller
2016   Feature Transfer Learning for Speech Emotion Recognition  J Deng
2016   Emotion Recognition in Speech with Deep Learning Architectures  M Erdal, M Kächele, F Schwenker
2016   Error-correcting output codes for multi-label emotion classification  C Li, Z Feng, C Xu
2016   Software Effort Estimation Framework To Improve Organization Productivity Using Emotion Recognition Of Software Engineers In …  BP Rao, PS Ramaiah
2016   How Deep Neural Networks Can Improve Emotion Recognition on Video Data  P Khorrami, TL Paine, K Brady, C Dagli, TS Huang
2016   Automatic emotion recognition in the wild using an ensemble of static and dynamic representations  MM Ghazi, HK Ekenel
2016   HoloNet: towards robust emotion recognition in the wild  A Yao, D Cai, P Hu, S Wang, L Sha, Y Chen
2016   Deep learning driven hypergraph representation for image-based emotion recognition  Y Huang, H Lu
2016   A Review on Deep Learning Algorithms for Speech and Facial Emotion Recognition  CP Latha, M Priya
2016   Novel Affective Features For Multiscale Prediction Of Emotion In Music  N Kumar, T Guha, CW Huang, C Vaz, SS Narayanan
2016   Facial emotion detection using deep learning  DL Spiers
2016   Speech Emotion Recognition Based on Deep Belief Networks and Wavelet Packet Cepstral Coefficients.  Y Huang, A Wu, G Zhang, Y Li
2016   Audio-Video Based Multimodal Emotion Recognition Using SVMs and Deep Learning  B Sun, Q Xu, J He, L Yu, L Li, Q Wei
2016   Feature Learning via Deep Belief Network for Chinese Speech Emotion Recognition  S Zhang, X Zhao, Y Chuang, W Guo, Y Chen
2016   Transfer Learning of Deep Neural Network for Speech Emotion Recognition  Y Huang, M Hu, X Yu, T Wang, C Yang
2016   Multiagent Social Influence Detection Based on Facial Emotion Recognition  P Mishra, R Hadfi, T Ito
2016   Emotion Recognition Using Facial Expression Images for a Robotic Companion  V Palade
2016   Emotion Recognition from Speech Signals Using Deep Learning Methods  S Pathak, MV Kolhe
2016   Multimodal Emotion Recognition Using Multimodal Deep Learning  W Liu, WL Zheng, BL Lu
2016   Self-Configuring Ensemble of Neural Network Classifiers for Emotion Recognition in the Intelligent Human-Machine Interaction  E Sopov, I Ivanov
2016   Facing Realism in Spontaneous Emotion Recognition from Speech: Feature Enhancement by Autoencoder with LSTM Neural Networks  Z Zhang, F Ringeval, J Han, J Deng, E Marchi
2016   The University of Passau Open Emotion Recognition System for the Multimodal Emotion Challenge  J Deng, N Cummins, J Han, X Xu, Z Ren, V Pandit
2016   Building a large scale dataset for image emotion recognition: The fine print and the benchmark  Q You, J Luo, H Jin, J Yang
2016   Emotion Recognition Using Multimodal Deep Learning  W Liu, WL Zheng, BL Lu
2016   Emotion Prediction from User-Generated Videos by Emotion Wheel Guided Deep Learning  CT Ho, YH Lin, JL Wu
2016   FDBN: Design and development of Fractional Deep Belief Networks for speaker emotion recognition  K Mannepalli, PN Sastry, M Suman
2016   A novel Adaptive Fractional Deep Belief Networks for speaker emotion recognition  K Mannepalli, PN Sastry, M Suman
2016   Unsupervised domain adaptation for speech emotion recognition using PCANet  Z Huang, W Xue, Q Mao, Y Zhan
2016   Learning Auditory Neural Representations for Emotion Recognition  P Barros, C Weber, S Wermter
2016   Towards an” In-the-Wild” Emotion Dataset Using a Game-based Framework  W Li, F Abtahi, C Tsangouri, Z Zhu
2016   Deep Learning for Emotion Recognition in Faces  A Ruiz
2016   Emotion Classification on face images  M Jorda, N Miolane, A Ng
2016   Paralinguistic Speech Recognition: Classifying Emotion in Speech with Deep Learning Neural Networks  ER Segal
2016   Architecture of Emotion in Robots Using Convolutional Neural Networks  M Ghayoumi, AK Bansal
2016   Emotion recognition from face dataset using deep neural nets  D Das, A Chakrabarty
2016   Recognize the facial emotion in video sequences using eye and mouth temporal Gabor features  PI Rani, K Muneeswaran
2016   Deep Learning Based Emotion Recognition from Chinese Speech  W Zhang, D Zhao, X Chen, Y Zhang
2016   Bi-Modal Music Emotion Recognition: Novel Lyrical Features and Dataset  R Malheiro, R Panda, P Gomes, R Paiva
2016   Speech Emotion Recognition Using Voiced Segment Selection Algorithm  Y Gu, E Postma, HX Lin, J van den Herik
2015   Multi-modal Dimensional Emotion Recognition using Recurrent Neural Networks  S Chen, Q Jin
2015   Quantification of Cinematography Semiotics for Video-based Facial Emotion Recognition in the EmotiW 2015 Grand Challenge  AC Cruz
2015   EEG Based Emotion Identification Using Unsupervised Deep Feature Learning  X Li, P Zhang, D Song, G Yu, Y Hou, B Hu
2015   Pattern-Based Emotion Classification on Social Media  E Tromp, M Pechenizkiy
2015   Investigating Critical Frequency Bands and Channels for EEG-based Emotion Recognition with Deep Neural Networks  WL Zheng, BL Lu
2015   Revealing critical channels and frequency bands for emotion recognition from EEG with deep belief network  WL Zheng, HT Guo, BL Lu
2015   Analysis of Physiological for Emotion Recognition with IRS Model  C Li, C Xu, Z Feng
2015   Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns  G Levi, T Hassner
2015   Negative Emotion Recognition in Spoken Dialogs  X Zhang, H Wang, L Li, M Zhao, Q Li
2015   Combining Multimodal Features within a Fusion Network for Emotion Recognition in the Wild  B Sun, L Li, G Zhou, X Wu, J He, L Yu, D Li, Q Wei
2015   A Deep Feature based Multi-kernel Learning Approach for Video Emotion Recognition  W Li, F Abtahi, Z Zhu
2015   Recurrent Neural Networks for Emotion Recognition in Video  S Ebrahimi Kahou, V Michalski, K Konda, R Memisevic
2015   Learning Speech Emotion Features by Joint Disentangling-Discrimination  W Xue, Z Huang, X Luo, Q Mao
2015   Data selection for acoustic emotion recognition: Analyzing and comparing utterance and sub-utterance selection strategies  D Le, EM Provost
2015   Leveraging Inter-rater Agreement for Audio-Visual Emotion Recognition  Y Kim, EM Provost
2015   The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid  X Shulan, W Jilin
2015   Optimized multi-channel deep neural network with 2D graphical representation of acoustic speech features for emotion recognition  MN Stolar, M Lech, IS Burnett
2015   EmoNets: Multimodal deep learning approaches for emotion recognition in video  SE Kahou, X Bouthillier, P Lamblin, C Gulcehre
2015   Deep learninig of EEG signals for emotion recognition  Y Gao, HJ Lee, RM Mehmood
2015   Emotion Recognition & Classification using Neural Networks  K Koupidis, A Ioannis
2015   Emotion recognition from embedded bodily expressions and speech during dyadic interactions  PM Müller, S Amin, P Verma, M Andriluka, A Bulling
2015   Speech emotion recognition with unsupervised feature learning  Z HUANG, W XUE, Q MAO
2015   Emotion identification by facial landmarks dynamics analysis  A Bandrabur, L Florea, C Florea, M Mancas
2014   Speech Emotion Recognition Using CNN  Z Huang, M Dong, Q Mao, Y Zhan
2014   Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video  L Chao, J Tao, M Yang, Y Li, Z Wen
2014   Improving generation performance of speech emotion recognition by denoising autoencoders  L Chao, J Tao, M Yang, Y Li
2014   Acoustic emotion recognition using deep neural network  J Niu, Y Qian, K Yu
2014   Prosodic, spectral and voice quality feature selection using a long-term stopping criterion for audio-based emotion recognition  M Kächele, D Zharkov, S Meudt, F Schwenker
2014   Emotion Modeling and Machine Learning in Affective Computing  K Kim
2014   Emotion Recognition in the Wild with Feature Fusion and Multiple Kernel Learning  JK Chen, Z Chen, Z Chi, H Fu
2014   A Study of Deep Belief Network Based Chinese Speech Emotion Recognition  B Chen, Q Yin, P Guo
Continue Reading

Overview of recent Deep Learning Bibliographies

For the last couple of months I’ve been creating bibliographies of recent academic publications in various subfields of Deep Learning on this blog. This posting gives an overview of the last 25 bibliographies posted.

Best regards,

Amund Tveit (WeChat: AmundTveit – Twitter: @atveit)

1. Deep Learning with Residual Networks

This posting is recent papers related to residual networks (i.e. very deep networks). Check out Microsoft Research’s paper Deep Residual Learning for Image Recognition and Kaiming He’s ICML 2016 Tutorial Deep Residual Learning, Deep Learning Gets Way Deeper

2. Deep Learning for Traffic Sign Detection and Recognition

Traffic Sign Detection and Recognition is key functionality for self-driving cars. This posting has recent papers in this area. Check also out related posting: Deep Learning for Vehicle Detection and Classification

3. Deep Learning for Vehicle Detection and Classification

This posting has recent papers about vehicle (e.g. car) detection and classification, e.g. for selv-driving/autonomous cars. Related: check also out Nvidia‘s End-to-End Deep Learning for Self-driving Cars and Udacity‘s Self-Driving Car Engineer (Nanodegree).

4. Deep Learning with Long Short-Term Memory (LSTM)

This blog post has some recent papers about Deep Learning with Long-Short Term Memory (LSTM). To get started I recommend checking out Christopher Olah’s Understanding LSTM Networks and Andrej Karpathy’s The Unreasonable Effectiveness of Recurrent Neural Networks. This blog post is complemented by Deep Learning with Recurrent/Recursive Neural Networks (RNN) — ICLR 2017 Discoveries.

5. Deep Learning in Finance

This posting has recent publications about Deep Learning in Finance (e.g. stock market prediction)

6. Deep Learning for Information Retrieval and Learning to Rank

This posting is about Deep Learning for Information Retrieval and Learning to Rank (i.e. of interest if developing search engines). The posting is complemented by the posting Deep Learning for Question Answering. To get started I recommend checking out Jianfeng Gao‘s (Deep Learning Technology Center at Microsoft Research) presentation Deep Learning for Web Search and Natural Language Processing.

Of partial relevance is the posting Deep Learning for Sentiment Analysis, the posting about Embedding for NLP with Deep Learning, the posting about Deep Learning for Natural Language Processing (ICLR 2017 discoveries), and the posting about Deep Learning for Recommender Systems

7. Deep Learning for Question Answering

This posting presents recent publications related to Deep Learning for Question Answering. Question Answering is described as “a computer science discipline within the fields of information retrieval and natural language processing (NLP), which is concerned with building systems that automatically answer questions posed by humans in a natural language”. I’ll also publish postings about Deep Learning for Information Retrieval and Learning to Rank today.

8. Ensemble Deep Learning

Ensemble Based Machine Learning has been used with success in several Kaggle competitions, and this year also the Imagenet competition was dominated by ensembles in Deep Learning, e.g. Trimps-Soushen team from 3rd Research Institute of the Ministry of Public Security (China) used a combination of Inception, Inception-Resnet, Resnet and Wide Residual Network to win the Object Classification/localization challenge. This blog post has recent papers related to Ensembles in Deep Learning.

9. Deep Learning for Sentiment Analysis

Recently I published Embedding for NLP with Deep Learning (e.g. word2vec and follow-ups) and Deep Learning for Natural Language Processing — ICLR 2017 Discoveries — this posting is also mostly NLP-related since it provides recent papers related to Deep Learning for Sentiment Analysis, but also has examples of other types of sentiment (e.g. image sentiment).

10. Deep Learning with Gaussian Process

Gaussian Process is a statistical model where observations are in the continuous domain, to learn more check out a tutorial on gaussian process(by Univ.of Cambridge’s Zoubin G.). Gaussian Process is an infinite-dimensional generalization of multivariate normal distributions.

Researchers from University of Sheffield — Andreas C. Damanianou and Neil D. Lawrence — started using Gaussian Process with Deep Belief Networks (in 2013). This Blog post contains recent papers related to combining Deep Learning with Gaussian Process.

11. Deep Learning for Clustering

12. Deep Learning in combination with EEG electrical signals from the brain

EEG (Electroencephalography) is the measurement of electrical signals in the brain. It has long been used for medical purposes (e.g. diagnosis of epilepsy), and has in more recent years also been used in Brain Computer Interfaces (BCI) — note: if BCI is new to you don’t get overly excited about it, since these interfaces are still in my opinion quite premature. But they are definitely interesting in a longer term perspective .

This blog post gives an overview of recent research on Deep Learning in combination with EEG, e.g. r for classification, feature representation, diagnosis, safety (cognitive state of drivers) and hybrid methods (Computer Vision or Speech Recognition together with EEG and Deep Learning).

13. Embedding for NLP with Deep Learning

Word Embedding was introduced by Bengio in early 2000s, and interest in it really accelerated when Google presented Word2Vec in 2013.

This blog post has recent papers related to embedding for Natural Language Processing with Deep Learning. Example application areas embedding is used for in the papers include finance (stock market prediction), biomedical text analysis, part-of-speech tagging, sentiment analysis, pharmacology (drug adverse effects).

I recommend you to start with the paper: In Defense of Word Embedding for Generic Text Representation

14. Zero-Shot (Deep) Learning

Zero-Shot Learning is making decisions after seing only one or few examples (as opposed to other types of learning that typically requires large amount of training examples). Recommend having a look at An embarrassingly simple approach to zero-shot learning first.

15. Deep Learning for Alzheimer Diagnostics and Decision Support

Alzheimer’s Disease is the cause of 60–70% of cases of Dementia, costs associated to diagnosis, treatment and care of patients with it is estimated to be in the range of a hundred billion dollars in USA. This blog post have some recent papers related to using Deep Learning for diagnostics and decision support related to Alzheimer’s disease.

16. Recommender Systems with Deep Learning

This blog post presents recent research in Recommender Systems (/collaborative filtering) with Deep Learning. To get started I recommend having a look at A Survey and Critique of Deep Learning in Recommender Systems.

17. Deep Learning for Ultrasound Analysis

Ultrasound (also called Sonography) are sound waves with higher frequency than humans can hear, they frequently used in medical settings, e.g. for checking that pregnancy is going well with fetal ultrasound. For more about Ultrasound data formats check out Ultrasound Research Interface. This blog post has recent publications about applying Deep Learning for analyzing Ultrasound data.

18. Deep Learning for Music

Deep Learning (creative AI) might potentially be used for music analysis and music creation. Deepmind’s Wavenet is a step in that direction. This blog post presents recent papers in Deep Learning for Music.

19. Regularized Deep Networks — ICLR 2017 Discoveries

This blog post gives an overview of papers related to using Regularization in Deep Learning submitted to ICLR 2017, see underneath for the list of papers. If you want to learn about Regularization in Deep Learning check out: www.deeplearningbook.org/contents/regularization.html

20. Unsupervised Deep Learning — ICLR 2017 Discoveries

This blog post gives an overview of papers related to Unsupervised Deep Learning submitted to ICLR 2017, see underneath for the list of papers. If you want to learn about Unsupervised Deep Learning check out: Ruslan Salkhutdinov’s video Foundations of Unsupervised Deep Learning.

21. Autoencoders in Deep Learning — ICLR 2017 Discoveries

This blog post gives an overview of papers related to autoencoders submitted to ICLR 2017, see underneath for the list of papers. If you want to learn about autoencoders check out the Stanford (UFLDL) tutorial about Autoencoders, Carl Doersch’ Tutorial on Variational Autoencoders, DeepLearning.TV’s Video tutorial on Autoencoders, or Goodfellow, Bengio and Courville’s Deep Learning book’s chapter on Autencoders.

22. Stochastic/Policy Gradients in Deep Learning — ICLR 2017 Discoveries

This blog post gives an overview of papers related to stochastic/policy gradient submitted to ICLR 2017, see underneath for the list of papers.

23. Deep Learning with Recurrent/Recursive Neural Networks (RNN) — ICLR 2017 Discoveries

This blog post gives an overview of Deep Learning with Recurrent/Recursive Neural Networks (RNN) related papers submitted to ICLR 2017, see underneath for the list of papers. If you want to learn more about RNN check out Andrej Karpathy’s The Unreasonable Effectiveness of Recurrent Neural Networks and Pascanu, Gulcehre, Cho and Bengio’s How to Construct Deep Recurrent Neural Networks.

24. Deep Learning with Generative and Generative Adverserial Networks — ICLR 2017 Discoveries

This blog post gives an overview of Deep Learning with Generative and Adverserial Networks related papers submitted to ICLR 2017, see underneath for the list of papers. Want to learn about these topics? See OpenAI’s article about Generative Models and Ian Goodfellow et.al’s paper about Generative Adversarial Networks.

25. Deep Learning for Natural Language Processing — ICLR 2017 Discoveries

This blog post gives an overview of Natural Language Processing related papers submitted to ICLR 2017, see underneath for the list of papers. If you want to learn about Deep Learning with NLP check out Stanford’s CS224d: Deep Learning for Natural Language Processing

Continue Reading

Deep Learning with Residual Networks

This posting is recent papers related to residual networks (i.e. very deep networks). Check out Microsoft Research’s paper Deep Residual Learning for Image Recognition and Kaiming He’s ICML 2016 Tutorial Deep Residual Learning, Deep Learning Gets Way Deeper

Best regards,
Amund Tveit

Year  Title Author
2016   Label distribution based facial attractiveness computation by deep residual learning  S Liu, B Li, Y Fan, Z Guo, A Samal
2016   Unsupervised Domain Adaptation with Residual Transfer Networks  M Long, J Wang, MI Jordan
2016   Deeper Depth Prediction with Fully Convolutional Residual Networks  I Laina, C Rupprecht, V Belagiannis, F Tombari
2016   Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis  Y Han, J Yoo, JC Ye
2016   Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex  Q Liao, T Poggio
2016   Deep Cross Residual Learning for Multitask Visual Recognition  B Jou, SF Chang
2016   Identity Mappings in Deep Residual Networks  K He, X Zhang, S Ren, J Sun
2016   Brain tumor classification of microscopy images using deep residual learning  Y Ishikawa, K Washiya, K Aoki, H Nagahashi
2016   Convolutional Residual Memory Networks  J Moniz, C Pal
2016   Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes  T Pohlen, A Hermans, M Mathias, B Leibe
2016   Aggregated Residual Transformations for Deep Neural Networks  S Xie, R Girshick, P Dollár, Z Tu, K He
2016   Deep residual networks for plankton classification  X Li, Z Cui
2016   Highway and Residual Networks learn Unrolled Iterative Estimation  K Greff, RK Srivastava, J Schmidhuber
2016   Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks  Y Cao, Z Wu, C Shen
2016   Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction  J Zhang, Y Zheng, D Qi
2016   Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising  K Zhang, W Zuo, Y Chen, D Meng, L Zhang
2016   Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning  C Szegedy, S Ioffe, V Vanhoucke
2016   Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution  W Yang, J Feng, J Yang, F Zhao, J Liu, Z Guo, S Yan
2016   FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics  TM Quan, DGC Hilderbrand, WK Jeong
2016   Deep Residual Hashing  S Conjeti, AG Roy, A Katouzian, N Navab
2016   Wide-Slice Residual Networks for Food Recognition  N Martinel, GL Foresti, C Micheloni
2016   VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation  H Chen, Q Dou, L Yu, PA Heng
2015   Current challenges in glioblastoma: intratumour heterogeneity, residual disease and models to predict disease recurrence  HP Ellis, M Greenslade, B Powell, I Spiteri, A Sottoriva
2014   Background Prior Based Salient Object Detection via Deep Reconstruction Residual  J Han, D Zhang, X Hu, L Guo, J Ren, F Wu
Continue Reading

Deep Learning for Traffic Sign Detection and Recognition

Traffic Sign Detection and Recognition is key functionality for self-driving cars. This posting has recent papers in this area. Check also out related posting: Deep Learning for Vehicle Detection and Classification

Best regards,
Amund Tveit
Amund Tveit

Year  Title Author
2016   Road surface traffic sign detection with hybrid region proposal and fast R-CNN  R Qian, Q Liu, Y Yue, F Coenen, B Zhang
2016   Traffic sign classification with deep convolutional neural networks  J CREDI
2016   Real-time Traffic Sign Recognition system with deep convolutional neural network  S Jung, U Lee, J Jung, DH Shim
2016   Traffic Sign Detection and Recognition using Fully Convolutional Network Guided Proposals  Y Zhu, C Zhang, D Zhou, X Wang, X Bai, W Liu
2016   A traffic sign recognition method based on deep visual feature  F Lin, Y Lai, L Lin, Y Yuan
2016   The research on traffic sign recognition based on deep learning  C Li, C Yang
2015   Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature  S Yin, P Ouyang, L Liu, Y Guo, S Wei
2015   Malaysia traffic sign recognition with convolutional neural network  MM Lau, KH Lim, AA Gopalai
2015   Negative-Supervised Cascaded Deep Learning for Traffic Sign Classification  K Xie, S Ge, R Yang, X Lu, L Sun
Continue Reading