Education
133 items from guillaume-chevalier/awesome-deep-learning-resources ★1,821
-
-
LSTM for Human Activity Recognition github.com
Recurrent Neural Network classification in TensorFlow with LSTM on cellphone sensor data
-
Neuraxle github.com
Sklearn-like framework for hyperparameter tuning and AutoML in deep learning projects.
-
Time series forecasting with Sequence-to-Sequence (seq2seq) rnn models github.com
Learn to use a seq2seq model on simple datasets as an introduction to the vast array of possibilities that this architecture offers
-
Simplified Scikit-learn Style Interface to TensorFlow github.com
TensorFlow wrapper à la scikit-learn.
-
-
-
-
Hyperopt for a Keras CNN on CIFAR-100 github.com
Auto (meta) optimizing a neural net (and its architecture) on the CIFAR-100 dataset.
-
Filtering signal, plotting the STFT and the Laplace transform github.com
Simple Python demo on signal processing.
-
SQuAD1.0 rajpurkar.github.io
Question answering dataset that can be explored online, and a list of models performing well on that dataset.
-
-
Machine Learning Course by Andrew Ng (Stanford University) coursera.org
Renown entry-level online class with certificate. Taught by: Andrew Ng, Associate Professor, Stanford University; Chief Scientist, Baidu; Chairman and Co-founder, Coursera.
-
Deep Learning deeplearningbook.org
Yet halfway through the book, it contains satisfying math content on how to think about actual deep learning.
-
Self Governing Neural Networks (SGNN): the Projection Layer github.com
With this, you can use words in your deep learning models without training nor loading embeddings.
-
Clean Machine Learning, a Coding Kata github.com
Learn the good design patterns to use for doing Machine Learning the good way, by practicing.
-
Migrating to Git LFS for Developing Deep Learning Applications with Large Files vooban.com
Easily manage huge files in your private Git projects.
-
Deep Residual Learning for Image Recognition arxiv.org
Very deep residual layers with batch normalization layers - a.k.a. "how to overfit any vision dataset with too many layers and make any vision model work properly at recognition given enough data".
-
Attention Is All You Need arxiv.org
(AIAYN) - Introducing multi-head self-attention neural networks with positional encoding to do sentence-level NLP without any RNN nor CNN - this paper is a must-read (also see this explanation and this visualization of the paper).
-
-
Hyperopt tutorial for Optimizing Neural Networks’ Hyperparameters vooban.com
Learn to slay down hyperparameter spaces automatically rather than by hand.
-
Discover structure behind data with decision trees vooban.com
Grow and plot a decision tree to automatically figure out hidden rules in your data
-
Understanding LSTM Networks colah.github.io
Explains the LSTM cells' inner workings, plus, it has interesting links in conclusion.
-
Neural Networks video series by Hugo Larochelle youtube.com
Interesting class about neural networks available online for free by Hugo Larochelle, yet I have watched a few of those videos.
-
Coursera Deep Learning Specialization coursera.org
New series of 5 Deep Learning courses by Andrew Ng, now with Python rather than Matlab/Octave, and which leads to a specialization certificate.
-
The Problem of Overfitting youtube.com
A good explanation of overfitting and how to address that problem.
-
Gradient Descent in Practice 2: Learning Rate youtube.com
How to adjust the learning rate of a neural network.
-
Diagnosing Bias vs Variance youtube.com
Understanding bias and variance in the predictions of a neural net and how to address those problems.
-
-
Attention Mechanisms in Recurrent Neural Networks (RNNs) - IGGG youtube.com
A talk for a reading group on attention mechanisms (Paper: Neural Machine Translation by Jointly Learning to Align and Translate).
- next page of items loading…
