Using keras-vis to debug self-driving model, toy example.
https://github.com/raghakot/keras-vis/blob/master/applications/self_driving/visualize_attention.ipynb
https://github.com/raghakot/keras-vis/blob/master/applications/self_driving/visualize_attention.ipynb
GitHub
raghakot/keras-vis
Neural network visualization toolkit for keras. Contribute to raghakot/keras-vis development by creating an account on GitHub.
OpenAI open sources a high-performance Python library for robotic simulation
https://blog.openai.com/faster-robot-simulation-in-python/
https://blog.openai.com/faster-robot-simulation-in-python/
OpenAI Blog
Faster Physics in Python
We're open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research. View CodeView Docs This library is one of our core tools for deep learning robotics research, which we've…
Attention in Long Short-Term Memory Recurrent Neural Networks
http://machinelearningmastery.com/attention-long-short-term-memory-recurrent-neural-networks/
http://machinelearningmastery.com/attention-long-short-term-memory-recurrent-neural-networks/
MachineLearningMastery.com
Attention in Long Short-Term Memory Recurrent Neural Networks - MachineLearningMastery.com
The Encoder-Decoder architecture is popular because it has demonstrated state-of-the-art results across a range of domains. A limitation of the architecture is that it encodes the input sequence to a fixed length internal representation. This imposes limits…
Автоэнкодеры в Keras, Часть 5: GAN(Generative Adversarial Networks) и tensorflow
https://habrahabr.ru/post/332000/
https://habrahabr.ru/post/332000/
Habr
Автоэнкодеры в Keras, Часть 5: GAN(Generative Adversarial Networks) и tensorflow
Содержание Часть 1: Введение Часть 2: Manifold learning и скрытые (latent) переменные Часть 3: Вариационные автоэнкодеры (VAE) Часть 4: Conditional VAE...
Автоэнкодеры в Keras, часть 6: VAE + GAN
https://habrahabr.ru/post/332074/
https://habrahabr.ru/post/332074/
Habr
Автоэнкодеры в Keras, часть 6: VAE + GAN
Содержание Часть 1: Введение Часть 2: Manifold learning и скрытые ( latent ) переменные Часть 3: Вариационные автоэнкодеры ( VAE ) Часть 4: Conditional VAE Часть 5: GAN (Generative Adversarial...
Gentle Introduction to the Adam Optimization Algorithm for Deep Learning
http://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/
http://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/
2nd Place Solution to 2017 Data Science Bowl
https://dhammack.github.io/kaggle-ndsb2017/
https://dhammack.github.io/kaggle-ndsb2017/
dhammack.github.io
2nd Place Solution to 2017 DSB - Daniel Hammack and Julian de Wit
Foreword
Tips for Training Recurrent Neural Networks
http://danijar.com/tips-for-training-recurrent-neural-networks/
http://danijar.com/tips-for-training-recurrent-neural-networks/
How to Visualize Your Recurrent Neural Network with Attention in Keras
https://medium.com/datalogue/attention-in-keras-1892773a4f22
https://medium.com/datalogue/attention-in-keras-1892773a4f22
Medium
How to Visualize Your Recurrent Neural Network with Attention in Keras
A technical discussion and tutorial
Improving LSTM-CTC based ASR performance in domains with limited training data
https://github.com/jb1999/eesen/blob/master/papers/LSTM-CTCperf2017.pdf
https://github.com/jb1999/eesen/blob/master/papers/LSTM-CTCperf2017.pdf
GitHub
jb1999/eesen
eesen - The official repository of the Eesen project
YellowFin: An automatic tuner for momentum SGD
http://cs.stanford.edu/~zjian/project/YellowFin/
http://cs.stanford.edu/~zjian/project/YellowFin/
Tensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks
https://github.com/jaesik817/pathnet
https://github.com/jaesik817/pathnet
GitHub
jaesik817/pathnet
pathnet - Tensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks
A TensorFlow implementation of “A neural autoregressive topic model”
http://blog.aylien.com/tensorflow-implementation-neural-autoregressive-topic-model-docnade/
http://blog.aylien.com/tensorflow-implementation-neural-autoregressive-topic-model-docnade/
AYLIEN
A TensorFlow implementation of "A neural autoregressive topic model" (DocNADE) - AYLIEN
In this post we give a brief overview of the DocNADE model, and provide a TensorFlow implementation.
When not to use deep learning
http://hyperparameter.space/blog/when-not-to-use-deep-learning/
http://hyperparameter.space/blog/when-not-to-use-deep-learning/
hyperparameter.space
When not to use deep learning
I know it’s a weird way to start a blog with a negative, but there was a wave of discussion in the last few days that I think serves as a good hook for some topics on which I’ve been thinking recently. It all started with a post in the Simply Stats blog by…
Evaluation code for various automated metrics for Natural Language Generation
https://github.com/Maluuba/nlg-eval
https://github.com/Maluuba/nlg-eval
GitHub
GitHub - Maluuba/nlg-eval: Evaluation code for various unsupervised automated metrics for Natural Language Generation.
Evaluation code for various unsupervised automated metrics for Natural Language Generation. - Maluuba/nlg-eval
What are the implications of relational reasoning (as talked about here) on NLP?
https://www.youtube.com/watch?v=vzg5Qe0pTKk&feature=youtu.be
https://www.youtube.com/watch?v=vzg5Qe0pTKk&feature=youtu.be
YouTube
DeepMind's AI Learns Superhuman Relational Reasoning | Two Minute Papers #168
The paper "A simple neural network module for relational reasoning" is available here: https://arxiv.org/abs/1706.01427 Details on our Patreon page: https://...