31
How Transformers Work – Model Used by Open AI and DeepMind
Transformers are a type of neural network architecture that have been gaining popularity. Transformers were recently used by OpenAI in…
32
33
34
A Visual Exploration of Gaussian Processes
Consulting software engineer and research scientist. I build visualization systems for complex data and machine learning models.
35
What’s the difference between statistics and machine learning?
I had an interesting discussion at work today (among people I think would all call themselves statisticians!) about the distinction(s) between statistics and machine learning. It is something I am …
36
The AI Threat to Open Societies
Good evening and thank you all for coming. I want to use my time tonight to warn the world about an unprecedented danger that’s threatening the very survival of open societies. Last year when I stood before you I spent most of my time analyzing the nefarious role of the IT monopolies. This is what […]
37
OpenGPT-2: We Replicated GPT-2 Because You Can Too
By Aaron Gokaslan* and Vanya Cohen*
38
AI competitions don’t produce useful models
Ai competitions are fun, community building, talent scouting, brand promoting, and attention grabbing. But competitions are not intended to develop useful models.
39
Taking ML to production with Rust
Hands-on technical leader, Rust expert.
40
Interpretable Machine Learning
Machine learning is part of our products, processes, and research. But computers usually don’t explain their predictions , which can cause many problems, ranging from trust issues to undetected bugs. This book is about making machine learning models and their decisions interpretable.
41
Logistic Regression from Bayes’ Theorem
In this post we’ll explore how we can derive logistic regression from Bayes’ Theorem. Starting with Bayes’ Theorem we’ll work our way to computing the log odds of our problem and the arrive at the inverse logit function. After reading this post you’ll have a much stronger intuition for how logistic
42
Principal component analysis: pictures, code and proofs (2018)
The code used to generate the plots for this post can be found here.
43
A sane introduction to maximum likelihood estimation and maximum a posteriori
It is frustrating to learn about principles such as maximum likelihood estimation (MLE), maximum a posteriori (MAP) and Bayesian inference in general. The main reason behind this difficulty, in my opinion, is that many tutorials assume previous knowledge, use implicit or inconsistent notation, or are even addressing a…
44
Neural Networks Are Essentially Polynomial Regression (2018)
You may be interested in my new arXiv paper, joint work with Xi Cheng, an undergraduate at UC Davis (now heading to Cornell for grad school); Bohdan Khomtchouk, a post doc in biology at Stanford; a…
45
Adventures Building a Self-Driving RC Car
Having read some amazing books on Machine Learning, I had been looking for opportunities to apply ML from first principles in the real world. That was what got me curious about the wonderful Donkey Car project. The project is essentially a how-to guide to building your own RC car which can drive itself around a track…
46
New chips for machine intelligence
This note summarises details of some of the new silicon chips for machine intelligence. Its aim is to distil the most important implementation and architectural details (at least those that are currently available), to highlight the main differences between them. I’m focusing on chips designed for training since they…
47
Neural ODE's: Understanding how they model data
In this blogpost I explore how ODE’s can be used to solve data modelling problems. I take a deep dive into the data modelling problem at hand and present ODE...
48
ML from Scratch, Part 2: Logistic Regression (2018)
In this second installment of the machine learning from scratch we switch the point of view from regression to classification: instead of estimating a number, we will be trying to guess which of 2 possible classes a given input belongs to. A modern example is looking at a photo and deciding if its a cat or a dog.
49
Graph Convolutional Networks (2016)
Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural...
50
Introduction to Bayesian Filter
Restate Some Basic Concepts and Math in Bayesian Filter
51
52
How to Begin a Novel
Last year for National Novel Writing Month I trained a neural net called torch-rnn on 10,096 unique ways to begin a novel. It came up with some intriguing possibilities, my personal favorite being “I am forced to write to my neighbors about the beast.” But many of its sentences used made-up words, or had such weird…
53
54
The Essential Tools of Scientific Machine Learning
Scientific machine learning is a burgeoning discipline which blends scientific computing and machine learning. Traditionally, scientific computing focuses on large-scale mechanistic models, usually differential equations, that are derived from scientific laws that simplified and explained phenomena. On the other hand…
55
Incremental Learning – A continuous learning approach (2018)
A few days back I read an article about how Bitcoin’s price can be sufficiently explained by Metcalfe’s law. As you read through the post, resist the temptation to click the links to learn more about Bitcoin, Metcalfe’s law etc. (Maybe you should read about Bitcoin if you have not heard of it). I have provided all the…
56
Automatic categorization of text is a core tool now
Get ready for medium data
57
Deep Learning: Our Miraculous Year 1990-1991
Many of the basic ideas behind the Deep Learning Revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" 1990-91
58
“The Book of Why” by Pearl and Mackenzie
Judea Pearl and Dana Mackenzie sent me a copy of their new book, “The book of why: The new science of cause and effect.”
59
Machine Learning: Full-Text Search in JavaScript – Relevance Scoring (2015)
Full-text search is a powerful machine learning algorithm, especially relevant for web developers. This article teaches you the basics, from scratch.
60