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.

  1. Clinical decision support for Alzheimer’s disease based on deep learning and brain network
    – Authors: C Hu, R Ju, Y Shen, P Zhou, Q Li (2016)
  2. Classification of Alzheimer’s Disease using fMRI Data and Deep Learning Convolutional Neural Networks
    – Authors: S Sarraf, G Tofighi (2016)
  3. Non-Invasive Detection of Alzheimerâ s Disease-Multifractality of Emotional Speech
    – Authors: S Bhaduri, R Das, D Ghosh (2016)
  4. Alzheimer’s Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network
    – Authors: E Hosseini (2016)
  5. Application of machine learning on postural control kinematics for the Diagnosis of Alzheimer’s disease
    – Authors: L Costa, Mf Gago, D Yelshyna, J Ferreira, Hd Silva… (2016)
  6. Multi-modality stacked deep polynomial network based feature learning for Alzheimer’s disease diagnosis
    – Authors: X Zheng, J Shi, Y Li, X Liu, Q Zhang (2016)
  7. Predicting Alzheimer’s disease: a neuroimaging study with 3D convolutional neural networks
    – Authors: A Payan, G Montana (2015)
  8. Linguistic Features Identify Alzheimer’s Disease in Narrative Speech
    – Authors: Kc Fraser, Ja Meltzer, F Rudzicz (2015)
  9. Detection of Alzheimer’s disease using group lasso SVM-based region selection
    – Authors: Z Sun, Y Fan, Bpf Lelieveldt, M Van De Giessen (2015)
  10. Anatomically Constrained Weak Classifier Fusion for Early Detection of Alzheimer’s Disease
    – Authors: D Domenger, P Coupé (2014)
Continue Reading

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.

Best regards,

Amund Tveit

  1. Less is more: zero-shot learning from online textual documents with noise suppression
    – Authors: R Qiao, L Liu, C Shen, A Hengel (2016)
  2. Synthesized Classifiers for Zero-Shot Learning
    – Authors: S Changpinyo, Wl Chao, B Gong, F Sha (2016)
  3. Tinkering Under The Hood: Interactive Zero-Shot Learning with Pictorial Classifiers
    – Authors: V Krishnan (2016)
  4. Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
    – Authors: E Gavves, T Mensink, T Tommasi, Cgm Snoek… (2015)
  5. Transductive Multi-view Zero-Shot Learning
    – Authors: Y Fu, Tm Hospedales, T Xiang, S Gong (2015)
  6. Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
    – Authors: J Ba, K Swersky, S Fidler, R Salakhutdinov (2015)
  7. Zero-Shot Learning with Structured Embeddings
    – Authors: Z Akata, H Lee, B Schiele (2014)
Continue Reading

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

Best regards,

Amund Tveit

  1. An approach to the use of word embeddings in an opinion classification task
    – Authors: F Enríquez, Ja Troyano, T López (2016)
  2. Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
    – Authors: B Li, T Liu, X Du, D Zhang, Z Zhao (2016)
  3. A Distributed Chinese Naive Bayes Classifier Based on Word Embedding
    – Authors: M Feng, G Wu (2016)
  4. An Empirical Study on Sentiment Classification of Chinese Review using Word Embedding
    – Authors: Y Lin, H Lei, J Wu, X Li (2015)
  5. Learning Bilingual Embedding Model for Cross-Language Sentiment Classification
    – Authors: X Tang, X Wan (2014)
  6. Training word embeddings for deep learning in biomedical text mining tasks
    – Authors: Z Jiang, L Li, D Huang, L Jin (2016)
  7. Learning Dense Convolutional Embeddings For Semantic Segmentation
    – Authors: Aw Harley, Kg Derpanis, I Kokkinos (2016)
  8. Creating Causal Embeddings for Question Answering with Minimal Supervision
    – Authors: R Sharp, M Surdeanu, P Jansen, P Clark, M Hammond (2016)
  9. Discriminative Phrase Embedding for Paraphrase Identification
    – Authors: W Yin, H Schütze (2016)
  10. Word embedding based retrieval model for similar cases recommendation
    – Authors: Y Zhao, J Wang, F Wang (2016)
  11. Learning Embeddings of API Tokens to Facilitate Deep Learning Based Program Processing
    – Authors: Y Lu, G Li, R Miao, Z Jin (2016)
  12. Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation
    – Authors: C Wei, S Luo, X Ma, H Ren, J Zhang, L Pan (2016)
  13. Deep Learning Architecture for Part-of-Speech Tagging with Word and Suffix Embeddings
    – Authors: A Popov (2016)
  14. Robobarista: Learning to Manipulate Novel Objects via Deep Multimodal Embedding
    – Authors: J Sung, Sh Jin, I Lenz, A Saxena (2016)
  15. Pruning subsequence search with attention-based embedding
    – Authors: C Raffel, Dpw Ellis (2016)
  16. Sentence Embedding Evaluation Using Pyramid Annotation
    – Authors: T Baumel, R Cohen, M Elhadad (2016)
  17. Deep Sentence Embedding Using the Long Short Term Memory Network: Analysis and Application to Information Retrieval
    – Authors: H Palangi, L Deng, Y Shen, J Gao, X He, J Chen… (2015)
  18. Feedback recurrent neural network-based embedded vector and its application in topic model
    – Authors: L Li, S Gan, X Yin (2016)
  19. Enhancing Sentence Relation Modeling with Auxiliary Character-level Embedding
    – Authors: P Li, H Huang (2016)
  20. Learning Word Meta-Embeddings by Using Ensembles of Embedding Sets
    – Authors: W Yin, H Schütze (2015)
  21. Syntax-Aware Multi-Sense Word Embeddings for Deep Compositional Models of Meaning
    – Authors: J Cheng, D Kartsaklis (2015)
  22. A Deep Embedding Model for Co-occurrence Learning
    – Authors: Y Shen, R Jin, J Chen, X He, J Gao, L Deng (2015)
  23. Jointly Modeling Embedding and Translation to Bridge Video and Language
    – Authors: Y Pan, T Mei, T Yao, H Li, Y Rui (2015)
  24. Learning semantic word embeddings based on ordinal knowledge constraints
    – Authors: Q Liu, H Jiang, S Wei, Zh Ling, Y Hu (2015)
  25. Boosting Named Entity Recognition with Neural Character Embeddings
    – Authors: C Dos Santos, V Guimaraes, Rj Niterói, R De Janeiro (2015)
  26. Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese
    – Authors: Er Fonseca, Jlg Rosa, Sm Aluísio (2015)
  27. Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
    – Authors: J Liu, K Zhao, B Kusy, J Wen, R Jurdak (2015)
  28. Learning Feature Hierarchies: A Layer-wise Tag-embedded Approach
    – Authors: Z Yuan, C Xu, J Sang, S Yan, M Hossain (2015)
  29. Multi-Source Bayesian Embeddings for Learning Social Knowledge Graphs
    – Authors: Z Yang, J Tang (2015)
  30. PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
    – Authors: J Tang, M Qu, Q Mei (2015)
  31. Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features
    – Authors: A Nikfarjam, A Sarker, K O’Connor, R Ginn, G Gonzalez (2015)
  32. Projective Label Propagation by Label Embedding
    – Authors: Z Zhang, W Jiang, F Li, L Zhang, M Zhao, L Jia (2015)
  33. An Investigation of Neural Embeddings for Coreference Resolution
    – Authors: V Godbole, W Liu, R Togneri (2015)
  34. Deep Multimodal Embedding: Manipulating Novel Objects with Point-clouds, Language and Trajectories
    – Authors: J Sung, I Lenz, A Saxena (2015)
  35. AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes
    – Authors: S Rothe, H Schütze (2015)
  36. Deep Multilingual Correlation for Improved Word Embeddings
    – Authors: A Lu, W Wang, M Bansal, K Gimpel, K Livescu (2015)
  37. Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
    – Authors: Y Peng, H Jiang (2015)
  38. The Impact of Structured Event Embeddings on Scalable Stock Forecasting Models
    – Authors: Jb Nascimento, M Cristo (2015)
  39. Representing Text for Joint Embedding of Text and Knowledge Bases
    – Authors: K Toutanova, D Chen, P Pantel, H Poon, P Choudhury… (2015)
  40. In Defense of Word Embedding for Generic Text Representation
    – Authors: G Lev, B Klein, L Wolf (2015)
  41. Learning Multi-Relational Semantics Using Neural-Embedding Models
    – Authors: B Yang, W Yih, X He, J Gao, L Deng (2014)
  42. Improving relation descriptor extraction with word embeddings and cluster features
    – Authors: T Liu, M Li (2014)
Continue Reading

Deep Learning in combination with EEG electrical signals from the brain

eeg

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).

Best regards,

Amund Tveit

Diagnosis and Medicine

  1. Classification of Epileptic EEG Signals with Stacked Sparse Autoencoder Based on Deep Learning
    – Authors: Q Lin, S Ye, X Huang, S Li, M Zhang, Y Xue, Ws Chen (2016)
  2. Advanced use of EEG in drug development and personalized medicine
    – Authors: S Simpraga, R Alvarez (2016)
  3. Low-complexity algorithms for automatic detection of sleep stages and events for use in wearable EEG systems
    – Authors: Sa Imtiaz (2016)
  4. Predicting epileptic seizure from Electroencephalography (EEG) using hilbert huang transformation and neural network
    – Authors: Mo Rahman, Mn Karim (2015)
  5. Multi-Channel EEG based Sleep Stage Classification with Joint Collaborative Representation and Multiple Kernel Learning
    – Authors: J Shi, X Liu, Y Li, Q Zhang, Y Li, S Yin (2015)
  6. Superchords: decoding EEG signals in the millisecond range
    – Authors: R Normand, Ha Ferreira (2015)
  7. A novel motor imagery EEG recognition method based on deep learning
    – Authors: M Li, M Zhang, Y Sun (2016)

Brain Computer Interfaces

  1. Convolutional Networks for EEG Signal Classification in Non-Invasive Brain-Computer Interfaces
    – Authors: E Forney, C Anderson, W Gavin, P Davies (2016)
  2. Using Deep Learning for Human Computer Interface via Electroencephalography
    – Authors: S Redkar (2016)
  3. Deep learning EEG response representation for brain computer interface
    – Authors: L Jingwei, C Yin, Z Weidong (2015)

Cognition and Emotion

  1. Single-channel EEG-based mental fatigue detection based on deep belief network
    – Authors: P Li, W Jiang, F Su (2016)
  2. EEG-based prediction of driver’s cognitive performance by deep convolutional neural network
    – Authors: M Hajinoroozi, Z Mao, Tp Jung, Ct Lin, Y Huang (2016)
  3. EEG-based Driver Fatigue Detection using Hybrid Deep Generic Model
    – Authors: Pp San, Sh Ling, R Chai, Y Tran, A Craig, Ht Nguyen (2016)
  4. Mental State Recognition via Wearable EEG
    – Authors: P Bashivan, I Rish, S Heisig (2016)
  5. Single trial prediction of normal and excessive cognitive load through EEG feature fusion
    – Authors: P Bashivan, M Yeasin, Gm Bidelman (2016)
  6. Prediction of driver’s drowsy and alert states from EEG signals with deep learning
    – Authors: M Hajinoroozi, Z Mao, Y Huang (2016)
  7. Investigating Critical Frequency Bands and Channels for EEG-based Emotion Recognition with Deep Neural Networks
    – Authors: Wl Zheng, Bl Lu (2015)
  8. Deep learninig of EEG signals for emotion recognition
    – Authors: Y Gao, Hj Lee, Rm Mehmood (2015)
  9. EEG Based Emotion Identification Using Unsupervised Deep Feature Learning
    – Authors: X Li, P Zhang, D Song, G Yu, Y Hou, B Hu (2015)
  10. Feature extraction with deep belief networks for driver’s cognitive states prediction from EEG data
    – Authors: M Hajinoroozi, Tp Jung, Ct Lin, Y Huang (2015)
  11. Measurement Of Stress Intensity Using Eeg
    – Authors: V Tóth (2015)
  12. Revealing critical channels and frequency bands for emotion recognition from EEG with deep belief network
    – Authors: Wl Zheng, Ht Guo, Bl Lu (2015)
  13. Interpretable Deep Neural Networks for Single-Trial EEG Classification
    – Authors: I Sturm, S Bach, W Samek, Kr Müller (2016)

Hybrid methods – combining Deep Learning and EEG with other Deep Learning methods

  1. Improving Electroencephalography-Based Imagined Speech Recognition with a Simultaneous Video Data Stream
    – Authors: Sj Stolze (2016)
  2. A closed-loop system for rapid face retrieval by combining EEG and computer vision
    – Authors: Y Wang, L Jiang, B Cai, Y Wang, S Zhang, X Zheng (2015)
  3. Emotional Affect Estimation Using Video and EEG Data in Deep Neural Networks
    – Authors: A Frydenlund, F Rudzicz (2015)

Feature representation and Classification

  1. Improving EEG feature learning via synchronized facial video
    – Authors: X Li, X Jia, G Xun, A Zhang (2016)
  2. Decoding EEG and LFP signals using deep learning: heading TrueNorth
    – Authors: E Nurse, Bs Mashford, Aj Yepes, I Kiral (2016)
  3. Fast and efficient rejection of background waveforms in interictal EEG
    – Authors: E Bagheri, J Jin, J Dauwels, S Cash, Mb Westover (2016)
  4. Class-wise Deep Dictionaries for EEG Classification
    – Authors: P Khurana, A Majumdar, R Ward (2016)
  5. EEG-based affect states classification using Deep Belief Networks
    – Authors: H Xu, Kn Plataniotis (2016)
  6. Feature Learning from Incomplete EEG with Denoising Autoencoder
    – Authors: J Li, Z Struzik, L Zhang, A Cichocki (2014)
  7. Joint optimization of algorithmic suites for EEG analysis
    – Authors: E Santana, Aj Brockmeier, Jc Principe (2014)
  8. Deep Extreme Learning Machine and Its Application in EEG Classification
    – Authors: S Ding, N Zhang, X Xu, L Guo, J Zhang (2014)
  9. Deep Feature Learning for EEG Recordings
    – Authors: S Stober, A Sternin, Am Owen, Ja Grahn (2015)
  10. A Multichannel Deep Belief Network for the Classification of EEG Data
    – Authors: Am Al (2015)
  11. Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
    – Authors: P Bashivan, I Rish, M Yeasin, N Codella (2015)
Continue Reading

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

  1. Mode Regularized Generative Adversarial Networks – Authors: Tong Che, Yanran Li, Athul Jacob, Yoshua Bengio, Wenjie Li
  2. Representation Stability as a Regularizer for Neural Network Transfer Learning – Authors: Matthew Riemer, Elham Khabiri, Richard Goodwin
  3. Neural Causal Regularization under the Independence of Mechanisms Assumption – Authors: Mohammad Taha Bahadori, Krzysztof Chalupka, Edward Choi, Walter F. Stewart, Jimeng Sun
  4. Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations – Authors: David Krueger, Tegan Maharaj, Janos Kramar, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh  Goyal, Yoshua Bengio, Aaron Courville, Christopher Pal
  5. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units – Authors: Dan Hendrycks, Kevin Gimpel
  6. Regularizing CNNs with Locally Constrained Decorrelations – Authors: Pau Rodríguez, Jordi Gonzàlez, Guillem Cucurull, Josep M. Gonfaus, Xavier Roca
  7. Regularizing Neural Networks by Penalizing Confident Output Distributions – Authors: Gabriel Pereyra, George Tucker, Jan Chorowski, Lukasz Kaiser, Geoffrey Hinton
  8. Multitask Regularization for Semantic Vector Representation of Phrases – Authors: Xia Song, Saurabh Tiwary \& Rangan Majumdar
  9. (F)SPCD: Fast Regularization of PCD by Optimizing Stochastic ML Approximation under Gaussian Noise – Authors: Prima Sanjaya, Dae-Ki Kang
  10. Crossmap Dropout : A Generalization of Dropout Regularization in Convolution Level – Authors: Alvin Poernomo, Dae-Ki Kang
  11. Non-linear Dimensionality Regularizer for Solving Inverse Problems – Authors: Ravi Garg, Anders Eriksson, Ian Reid
  12. Support Regularized Sparse Coding and Its Fast Encoder – Authors: Yingzhen Yang, Jiahui Yu, Pushmeet Kohli, Jianchao Yang, Thomas S. Huang
  13. An Analysis of Feature Regularization for Low-shot Learning – Authors: Zhuoyuan Chen, Han Zhao, Xiao Liu, Wei Xu
  14. Dropout with Expectation-linear Regularization – Authors: Xuezhe Ma, Yingkai Gao, Zhiting Hu, Yaoliang Yu, Yuntian Deng, Eduard Hovy
  15. SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks – Authors: Armen Aghajanyan
Continue Reading

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.

Best regards,
Amund Tveit

  1. Unsupervised Learning Using Generative Adversarial Training And Clustering – Authors: Vittal Premachandran, Alan L. Yuille
  2. An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax – Authors: Wentao Huang, Kechen Zhang
  3. Unsupervised Cross-Domain Image Generation – Authors: Yaniv Taigman, Adam Polyak, Lior Wolf
  4. Unsupervised Perceptual Rewards for Imitation Learning – Authors: Pierre Sermanet, Kelvin Xu, Sergey Levine
  5. Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning – Authors: William Lotter, Gabriel Kreiman, David Cox
  6. Unsupervised sentence representation learning with adversarial auto-encoder – Authors: Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang
  7. Unsupervised Program Induction with Hierarchical Generative Convolutional Neural Networks – Authors: Qucheng Gong, Yuandong Tian, C. Lawrence Zitnick
  8. Generalizable Features From Unsupervised Learning – Authors: Mehdi Mirza, Aaron Courville, Yoshua Bengio
  9. Reinforcement Learning with Unsupervised Auxiliary Tasks – Authors: Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu
  10. Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data – Authors: Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt
  11. Unsupervised Learning of State Representations for Multiple Tasks – Authors: Antonin Raffin, Sebastian Höfer, Rico Jonschkowski, Oliver Brock, Freek Stulp
  12. Unsupervised Pretraining for Sequence to Sequence Learning – Authors: Prajit Ramachandran, Peter J. Liu, Quoc V. Le
  13. Unsupervised Deep Learning of State Representation Using Robotic Priors – Authors: Timothee LESORT, David FILLIAT
  14. Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders – Authors: Nat Dilokthanakul, Pedro A. M. Mediano, Marta Garnelo, Matthew C.H. Lee, Hugh Salimbeni, Kai Arulkumaran, Murray Shanahan
  15. Deep unsupervised learning through spatial contrasting – Authors: Elad Hoffer, Itay Hubara, Nir Ailon

Sign up for Deep Learning newsletter!


Continue Reading

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.

Best regards,

Amund Tveit

  1. Revisiting Denoising Auto-Encoders – Authors: Luis Gonzalo Sanchez Giraldo
  2. Epitomic Variational Autoencoders – Authors: Serena Yeung, Anitha Kannan, Yann Dauphin, Li Fei-Fei
  3. Unsupervised sentence representation learning with adversarial auto-encoder – Authors: Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang
  4. Tree-Structured Variational Autoencoder – Authors: Richard Shin, Alexander A. Alemi, Geoffrey Irving, Oriol Vinyals
  5. Lossy Image Compression with Compressive Autoencoders – Authors: Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár
  6. Variational Lossy Autoencoder – Authors: Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, Pieter Abbeel
  7. Stick-Breaking Variational Autoencoders – Authors: Eric Nalisnick, Padhraic Smyth
  8. ParMAC: distributed optimisation of nested functions, with application to binary autoencoders – Authors: Miguel A. Carreira-Perpinan, Mehdi Alizadeh
  9. Discrete Variational Autoencoders – Authors: Jason Tyler Rolfe
  10. Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders – Authors: Nat Dilokthanakul, Pedro A. M. Mediano, Marta Garnelo, Matthew C.H. Lee, Hugh Salimbeni, Kai Arulkumaran, Murray Shanahan
  11. Improving Sampling from Generative Autoencoders with Markov Chains – Authors: Kai Arulkumaran, Antonia Creswell, Anil Anthony Bharath

Sign up for Deep Learning newsletter!


Continue Reading

Stochastic/Policy Gradients in Deep Learning – ICLR 2017 Discoveries

The 5th International Conference on Learning Representation (ICLR 2017) is coming to Toulon, France (April 24-26 2017).

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

Best regards,
Amund Tveit

  1. Improving Policy Gradient by Exploring Under-appreciated Rewards – Authors: Ofir Nachum, Mohammad Norouzi, Dale Schuurmans
  2. Leveraging Asynchronicity in Gradient Descent for Scalable Deep Learning – Authors: Jeff Daily, Abhinav Vishnu, Charles Siegel
  3. Adding Gradient Noise Improves Learning for Very Deep Networks – Authors: Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Lukasz Kaiser, Karol Kurach, Ilya Sutskever, James Martens
  4. Inefficiency of stochastic gradient descent with larger mini-batches (and more learners) – Authors: Onkar Bhardwaj, Guojing Cong
  5. Improving Stochastic Gradient Descent with Feedback – Authors: Jayanth Koushik, Hiroaki Hayashi
  6. PGQ: Combining policy gradient and Q-learning – Authors: Brendan O’Donoghue, Remi Munos, Koray Kavukcuoglu, Volodymyr Mnih
  7. SGDR: Stochastic Gradient Descent with Restarts – Authors: Ilya Loshchilov, Frank Hutter
  8. Neural Data Filter for Bootstrapping Stochastic Gradient Descent – Authors: Yang Fan, Fei Tian, Tao Qin, Tie-Yan Liu
  9. Entropy-SGD: Biasing Gradient Descent Into Wide Valleys – Authors: Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun
  10. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic – Authors: Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine
  11. Batch Policy Gradient Methods for Improving Neural Conversation Models – Authors: Kirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka, Daniel Tarlow, David Carter
  12. Training Long Short-Term Memory With Sparsified Stochastic Gradient Descent – Authors: Maohua Zhu, Minsoo Rhu, Jason Clemons, Stephen W. Keckler, Yuan Xie
  13. Parallel Stochastic Gradient Descent with Sound Combiners – Authors: Saeed Maleki, Madanlal Musuvathi, Todd Mytkowicz, Yufei Ding
  14. Gradients of Counterfactuals – Authors: Mukund Sundararajan, Ankur Taly, Qiqi Yan

Sign up for Deep Learning newsletter!


Continue Reading

Deep Learning with Recurrent/Recursive Neural Networks (RNN) – ICLR 2017 Discoveries

The 5th International Conference on Learning Representation (ICLR 2017) is coming to Toulon, France (April 24-26 2017).

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 Networksand Pascanu, Gulcehre, Cho and Bengio’s How to Construct Deep Recurrent Neural Networks.

Best regards,
Amund Tveit

  1. Making Neural Programming Architectures Generalize via Recursion – Authors: Jonathon Cai, Richard Shin, Dawn Song
  2. Multi-label learning with the RNNs for Fashion Search – Authors: Taewan Kim
  3. Recursive Regression with Neural Networks: Approximating the HJI PDE Solution – Authors: Vicenç Rubies Royo
  4. SampleRNN: An Unconditional End-to-End Neural Audio Generation Model – Authors: Soroush Mehri, Kundan Kumar, Ishaan Gulrajani, Rithesh Kumar, Shubham Jain, Jose Manuel Rodriguez Sotelo, Aaron Courville, Yoshua Bengio
  5. Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations – Authors: David Krueger, Tegan Maharaj, Janos Kramar, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron Courville, Christopher Pal
  6. LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation – Authors: Jianwei Yang, Anitha Kannan, Dhruv Batra, Devi Parikh
  7. TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency – Authors: Adji B. Dieng, Chong Wang, Jianfeng Gao, John Paisley

Sign up for Deep Learning newsletter!


Continue Reading

Deep Learning with Reinforcement Learning – ICLR 2017 Discoveries

The 5th International Conference on Learning Representation (ICLR 2017) is coming to Toulon, France (April 24-26 2017).

This blog post gives an overview of Deep Learning with Reinforcement related papers submitted to ICLR 2017, see underneath for the list of papers. If you want to learn more about combining Deep Learning with Reinforcement Learning check out Nervana’s Demystifying Deep Reinforcement Learning, Andrej Karpathy’s Deep Reinforcement Learning: Pong From Pixels, DeepMind’s Deep Reinforcement Learning, and Berkeley University’s CS 294: Deep Reinforcement Learning (starting in Sprint 2017)

Best regards,

Amund Tveit

ICLR 2017 – Reinforcement Related paper

  1. Stochastic Neural Networks for Hierarchical Reinforcement Learning – Authors: Carlos Florensa, Yan Duan, Pieter Abbeel
  2. #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning – Authors: Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel
  3. Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning – Authors: Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, Sergey Levine
  4. Deep Reinforcement Learning for Accelerating the Convergence Rate – Authors: Jie Fu, Zichuan Lin, Danlu Chen, Ritchie Ng, Miao Liu, Nicholas Leonard, Jiashi Feng, Tat-Seng Chua
  5. Generalizing Skills with Semi-Supervised Reinforcement Learning – Authors: Chelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine
  6. Learning to Perform Physics Experiments via Deep Reinforcement Learning – Authors: Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas
  7. Designing Neural Network Architectures using Reinforcement Learning – Authors: Bowen Baker, Otkrist Gupta, Nikhil Naik, Ramesh Raskar
  8. Reinforcement Learning with Unsupervised Auxiliary Tasks -Authors: Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu
  9. Options Discovery with Budgeted Reinforcement Learning – Authors: Aurelia Lon, Ludovic Denoyer
  10. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU – Authors: Mohammad Babaeizadeh, Iuri Frosio, Stephen Tyree, Jason Clemons,Jan Kautz
  11. Multi-task learning with deep model based reinforcement learning – Authors: Asier Mujika
  12. Neural Architecture Search with Reinforcement Learning -Authors: Barret Zoph, Quoc Le
  13. Tuning Recurrent Neural Networks with Reinforcement Learning -Authors: Natasha Jaques, Shixiang Gu, Richard E. Turner, Douglas Eck
  14. RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning – Authors: Yan Duan, John Schulman, Xi Chen, Peter Bartlett, Ilya Sutskever, Pieter Abbeel
  15. Learning to Repeat: Fine Grained Action Repetition
    for Deep Reinforcement Learning
    – Authors: Sahil Sharma, Aravind S. Lakshminarayanan, Balaraman Ravi
    ndran
  16. Learning to Play in a Day: Faster Deep Reinforcemen
    t Learning by Optimality Tightening
    – Authors: Frank S.He, Yang Liu, Alexander G. Schwing, Jian Peng
  17. Surprise-Based Intrinsic Motivation for Deep Reinfo
    rcement Learning
    – Authors: Joshua Achiam, Shankar Sastry
  18. Learning to Compose Words into Sentences with Reinf
    orcement Learning
    – Authors: Dani Yogatama, Phil Blunsom, Chris Dyer, Edward Grefenstette, Wang Ling
  19. Spatio-Temporal Abstractions in Reinforcement Learn
    ing Through Neural Encoding
    – Authors: Nir Baram, Tom Zahavy, Shie Mannor
  20. Modular Multitask Reinforcement Learning with Policy Sketches – Authors: Jacob Andreas, Dan Klein, Sergey Levine
  21. Combating Deep Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear – Authors: Zachary C. Lipton, Jianfeng Gao, Lihong Li, Jianshu Chen, Li Deng

Sign up for Deep Learning newsletter!


Continue Reading