Computer Science
7,622 items in 38 lists
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
Paper arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] arxiv.org
-
[arXiv Paper] arxiv.org
-
[Paper] arxiv.org
-
[Paper] ais.uni-bonn.de
-
[Paper] ais.uni-bonn.de
-
Paper 202.118.75.4
-
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.
-
Gradient Descent: Intuition youtube.com
What follows from the previous video: now add intuition.
-
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).
-
Growing Neat Software Architecture from Jupyter Notebooks youtube.com
A primer on how to structure your Machine Learning projects when using Jupyter Notebooks.
-
Gradient Descent youtube.com
Okay, I already listed Andrew NG's Coursera class above, but this video especially is quite pertinent as an introduction and defines the gradient descent algorithm.
-
Deep Learning Lecture 12: Recurrent Neural Nets and LSTMs youtube.com
Unfolding of RNN graphs is explained properly, and potential problems about gradient descent algorithms are exposed.
-
Two Minute Papers' Channel youtube.com
Interesting and shallow overview of some research papers, for example about WaveNet or Neural Style Transfer.
-
Computer Science youtube.com
Yet another YouTube playlist I composed, this time about various CS topics.
-
Signal Processing Playlist youtube.com
A YouTube playlist I composed about DFT/FFT, STFT and the Laplace transform - I was mad about my software engineering bachelor not including signal processing classes (except a bit in the quantum physics class).
-
Deep Learning & Machine Learning (Advanced topics) youtube.com
A list of videos about deep learning that I found interesting or useful, this is a mix of a bit of everything.
-
Tensor Calculus and the Calculus of Moving Surfaces youtube.com
Generalize properly how Tensors work, yet just watching a few videos already helps a lot to grasp the concepts.
-
Siraj's Channel youtube.com
Siraj has entertaining, fast-paced video tutorials about deep learning.
-
What is the Best Multi-Stage Architecture for Object Recognition? yann.lecun.com
Awesome for the use of "local contrast normalization".
-
Neuralink and the Brain’s Magical Future waitbutwhy.com
Thought provoking article about the future of the brain and brain-computer interfaces.
-
Why do 87% of data science projects never make it into production? venturebeat.com
Data is not to be overlooked, and communication between teams and data scientists is important to integrate solutions properly.
-
SOLID Machine Learning umaneo.com
The SOLID principles applied to Machine Learning.
-
GLO-4030/7030 Apprentissage par réseaux de neurones profonds ulaval-damas.github.io
This is a class given by Philippe Giguère, Professor at University Laval. I especially found awesome its rare visualization of the multi-head attention mechanism, which can be contemplated at the slide 28 of week 13's class.
-
Machine Learning for Trading by Georgia Tech udacity.com
Interesting class for acquiring basic knowledge of machine learning applied to trading and some AI and finance concepts. I especially liked the section on Q-Learning.
-
Deep Learning by Google udacity.com
Good intermediate to advanced-level course covering high-level deep learning concepts, I found it helps to get creative once the basics are acquired.
-
François Chollet's Twitter twitter.com
Author of Keras - has interesting Twitter posts and innovative ideas.
-
The real reason most ML projects fail towardsdatascience.com
Focus on clear business objectives, avoid pivots of algorithms unless you have really clean code, and be able to know when what you coded is "good enough".
-
NLP's ImageNet moment has arrived thegradient.pub
All hail NLP's ImageNet moment.
-
Gradient descent algorithms in a saddle point sebastianruder.com
Visualize how different optimizers interacts with a saddle points.
-
Improving Inception and Image Classification in TensorFlow research.googleblog.com
Very interesting CNN architecture (e.g.: the inception-style convolutional layers is promising and efficient in terms of reducing the number of parameters).
-
Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source research.googleblog.com
Parsey McParseface's birth, a neural syntax tree parser.
-
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour research.fb.com
Incredibly fast distributed training of a CNN.
-
Sequence to Sequence Learning with Neural Networks papers.nips.cc
4 stacked LSTM cells of 1000 hidden size with reversed input sentences, and with beam search, on the WMT’14 English to French dataset.
-
LibriSpeech ASR corpus openslr.org
Huge free English speech dataset with balanced genders and speakers, that seems to be of high quality.
- next page of items loading…
