31
Why deep learning works even though it shouldn’t
Why models always get better when they are bigger and deeper, even when the amount of data they consume stays the same or gets smaller.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 212 posts.
32
Using machine learning to recreate photorealistic portraits of Roman Emperors
Artistic interpretations of the 54 Roman emperors of the Principate, created with AI and historical references.
33
ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations
Posted by Radu Soricut and Zhenzhong Lan, Research Scientists, Google Research Ever since the advent of BERT a year ago, natural language research...
34
35
T5: The Text-to-Text Transfer Transformer
Posted by Adam Roberts, Staff Software Engineer and Colin Raffel, Senior Research Scientist, Google Research Over the past few years, transfer le...
36
Teaching GPT-3 to Identify Nonsense
In Giving GPT-3 a Turing Test, Kevin Lacker found that GPT-3 does well answering simple factual questions like “Who was president of the United States in 1955?”, but also happily answered absurd qu…
37
Does GPT-2 Know Your Phone Number?
The BAIR Blog
38
Deep Learning for Guitar Effect Emulation
Since the 1940s, electric guitarists, keyboardists, and other instrumentalists have been using effects pedals, devices that modify the sound of the original audio source. Typical effects include distortion, compression, chorus, reverb, and delay. Early effects pedals consisted of basic analog circuits, often along…
39
What is protein folding? A brief explanation
AlphaFold from Google DeepMind is said to solve the protein folding problem. What is that, and why is it hard?
40
All models are wrong, but some are completely wrong
At this critical time in the modern history of the human race, mathematical models have been pushed into the foreground. Epidemic forecasting informs policy and even individual decision-making. Sad…
41
What I wish someone had told me about tensor computation libraries
I get confused with tensor computation libraries (or computational graph libraries, or symbolic algebra libraries, or whatever they’re marketing themselves as these days). I was first introduced to PyTorch and TensorFlow and, having no other reference, thought they were prototypical examples of tensor computation…
42
Using GANs to Create Fantastical Creatures
Posted by Andeep Singh Toor, Stadia Software Engineer and Fred Bertsch, Software Engineer, Google Research, Brain Team Creating art for digital vid...
43
Pac-Man recreated with a GAN trained on 50k game episodes
Bringing together the world’s brightest minds and the latest accelerated computing technology leads to powerful breakthroughs that help tackle some of the biggest research problems....
44
GPT-3
May 2020 Gwern.net newsletter: GPT-3 scaling, implications, deep theory; anime GAN updates, and 1 book review.
45
Autocomplete as an Interface (2015)
the real reason zsh beats bash • how I got twice as fast in python • autocompleting all the things • maximizing user-interface bandwidth
46
Building an end-to-end Speech Recognition model in PyTorch
The complete guide on how to build an end-to-end Speech Recognition model in PyTorch. Train your own CTC Deep Speech model using this tutorial.
47
Dopamine and Temporal Difference Learning
Learning and motivation are driven by internal and external rewards. Many of our day-to-day behaviours are guided by predicting, or anticipating, whether a given action will result in a positive (that is, rewarding) outcome. The study of how organisms learn from experience to correctly anticipate rewards has been a…
48
Nvidia announces Jetson Nano 2GB, a single board computer
Using Python 3.6, OpenCV, Dlib and the face_recognition module
49
Nvidia’s Integration Dreams
Nvidia’s acquisition of ARM only makes sense from a financial perspective, unless you buy Jensen Huang’s datacenter dreams.
50
Testing Firefox more efficiently with machine learning
A browser is an enormously complex piece of software, and it's always in development. About a year ago, we asked ourselves: how could we do better? Our CI relied heavily ...
51
52
Recent Advances in Natural Language Processing
Deponysum membahas konsep filsafat, kecerdasan buatan, ekonomi, dan kritik sastra secara edukatif untuk memperluas wawasan dan cara berpikir kritis.
53
I asked GPT-3 for the question to “42”
Can GPT-3 compute the ultimate question about life, the Universe and everything?
54
Image GPT
We find that, just as a large transformer model trained on language can generate coherent text, the same exact model trained on pixel sequences can generate coherent image completions and samples. By establishing a correlation between sample quality and image classification accuracy, we show that our best generative…
55
Tempering Expectations for GPT-3 and OpenAI’s API
GPT-3 is indeed a large step forward for AI text-generation, but there are very many caveats with the popular demos and use cases.
56
57
Tensorflow on edge, or – Building a “smart” security camera with a Raspberry Pi
The amount of time my outdoor cameras are being set off by light, wind, cars, or anything other than a human is insane. Overly cautious security cameras might be a feature, but an annoying one at that...
58
59
Netflix's Metaflow: Reproducible machine learning pipelines
A complete guide to building end-to-end machine learning pipelines, from training to deployment, with Metaflow and Cortex
60