1
Visual Information Theory (2015)
I love the feeling of having a new way to think about the world. I especially love when there’s some vague idea that gets formalized into a concrete concept. Information theory is a prime example of this.
Christopher Olah
Writing rough notes allows me share more content, since polishing takes lots of time. While I hope it's useful, it's likely lower quality and less carefully considered than my usual articles.
- Popular posts
- 9
- Total points
- 2,121
- HN comments
- 563
- Rank
- #770 personal
Visit colah.github.io → On Hacker News Apr 2014 – Jan 2024
AI & Machine Learning 7Math & Algorithms 6Software Engineering 2Life, Learning & Writing 2Career & Management 1
2
I've decided to move on to Distill
I do not plan to write more of my deep learning articles on this site. Instead, I will be co-editor of Distill , a visual, interactive journal for machine learning research emphasizing human understanding. I believe this will allow me to better serve the community.
3
Neural Networks, Manifolds, and Topology
Recently, there’s been a great deal of excitement and interest in deep neural networks because they’ve achieved breakthrough results in areas such as computer vision. 1
4
Neural Networks, Types, and Functional Programming
Deep learning, despite its remarkable successes, is a young field. While models called artificial neural networks have been studied for decades, much of that work seems only tenuously connected to modern results.
5
Do I need to go to university?
Instead of asking “Is university good?”, ask “Do I have something more compelling to do?”. Instead of “Should I do a PhD?”, ask “Where can I find the best environment to grow as a researcher?”.
6
Calculus on Computational Graphs: Backpropagation (2015)
Backpropagation is the key algorithm that makes training deep models computationally tractable. For modern neural networks, it can make training with gradient descent as much as ten million times faster, relative to a naive implementation. That’s the difference between a model taking a week to train and taking 200,000…
7
Understanding Convolutions (2014)
neural networks , convolutional neural networks , convolution , math , probability
8
Deep Learning, NLP, and Representations
neural networks , deep learning , representations , NLP , recursive neural networks
9
Understanding LSTM Networks (2015)
Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You don’t throw everything away and start thinking from scratch again. Your thoughts have persistence.