91
Transformers from Scratch
Repository for personal website
New
The latest blog posts to take off on Hacker News. 262 posts.
92
OpenGPT-2: We Replicated GPT-2 Because You Can Too
By Aaron Gokaslan* and Vanya Cohen*
93
Deep Learning Illustrated: Building Natural Language Processing Models
A hands-on guide to natural language processing with Keras. Covers word2vec, sentiment classification, CNNs, RNNs, and LSTMs using the IMDb dataset in Python.
94
How to Start with Machine Learning
In this article, I'd like to tell you how to start with machine learning, and what to do to learn algorithms that will help you to build smart apps.
95
96
97
GPT-2: 6-Month Follow-Up
We’re releasing the 774 million parameter GPT-2 language model after the release of our small 124M model in February, staged release of our medium 355M model in May, and subsequent research with partners and the AI community into the model’s potential for misuse and societal benefit. We’re also releasing an…
98
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…
99
Python vs. Rust for Neural Networks
Comparing a simple neural network in Rust and Python
100
Siri, Privacy, and Trust
We should expect Apple to lead the industry on this front, but in fact, they’re far behind.
101
102
Camera vs. Lidar
Company updates and technology articles from Scale AI.
103
104
Vibration-minimizing motion retargeting for robotic characters
Creating animations for robotic characters is very challenging due to the constraints imposed by their physical nature. In particular, the combination of fast motions and unavoidable structural deformations leads to mechanical oscillations that negatively affect their performances. Our goal is to automatically…
105
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 …
106
Building a State of the Art Bacterial Classifier with Fast.ai and Paperspace
In this post, we’re going to be demonstrating how to to build a state of the art Bacterial Classification model on Gradient using the Fast.ai machine learning library.
107
108
SpaCy PyTorch Transformers
Huge transformer models like BERT, GPT-2 and XLNet have set a new standard for accuracy on almost every NLP leaderboard. You can now use these models in spaCy, via a new interface library we've developed that connects spaCy to Hugging Face's awesome implementations.
109
Advances in Conversational AI
Facebook AI has made scientific progress in improving nuanced conversational skills, including consistency, specificity, and empathy.
110
111
Introduction to Bayesian Filter
Restate Some Basic Concepts and Math in Bayesian Filter
112
Amazon Transcribe Streaming Now Supports WebSockets
I love services like Amazon Transcribe. They are the kind of just-futuristic-enough technology that excites my imagination the same way that magic does. It’s incredible that we have accurate, automatic speech recognition for a variety of languages and accents, in real-time. There are so many use-cases, and nearly all…
113
An Introduction to Recurrent Neural Networks
A simple walkthrough of what RNNs are, how they work, and how to build one from scratch in Python.
114
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.
115
How we built the Waifu Vending Machine
On the weekend of Anime Expo, an artist promised the humanly impossible -- custom art commissions with a five-minute turnaround time. The not-so-hidden catch? The artist wasn't a human at all, but an AI exposed to millions of anime images.
116
117
Lyft releases self-driving research dataset
By Luc Vincent, EVP Autonomous Technology
118
L2 Regularization and Batch Norm
This blog post is about an interesting detail about machine learning that I came across as a researcher at Jane Street - that of the interaction between L2 r...
119
An Analysis of WeChat’s Realtime Image Filtering in Chats
In this work, we study how Tencent implements image filtering on WeChat. We found that Tencent implements realtime, automatic censorship of chat images on WeChat based on what text is in an image and based on an image’s visual similarity to those on a blacklist. Tencent facilitates this realtime filtering by…
120
Microsoft is investing $1B in OpenAI
Microsoft is investing $1 billion in OpenAI to support us building artificial general intelligence (AGI) with widely distributed economic benefits. We’re partnering to develop a hardware and software platform within Microsoft Azure which will scale to AGI. We’ll jointly develop new Azure AI supercomputing…