Visualizing the Impact of Feature Attribution Baselines
Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior.
Uncategorised
deep-learning, Machine Learning
Book Review: Architects of Intelligence by Martin Ford
A brief review of Martin Ford’s book that features interviews with 23 of the most well-known and brightest minds working on AI.
ai
Selected Quotes from "The Dark Ages of AI Panel Discussion"
In 1984, a panel at the AAAI conference discussed whether the field was approaching an “AI Winter”. Mitch Waldrop wrote a transcript of the discussion, and much of it reads exactly like something written 35 years into the future.
Below are s…
deep-learning, Machine Learning
What’s New in the 3rd Edition
A brief summary of what’s new in the 3rd edition of Python Machine Learning.
Research
Deep double descent
We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through car…
Research
Procgen Benchmark
We’re releasing Procgen Benchmark, 16 simple-to-use procedurally-generated environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills.
deep-learning, graphics
Differentiable Path Tracing on the GPU/TPU
You can download a PDF (typset in LaTeX) of this blog post here.
Jupyter Notebook Code on GitHub: https://github.com/ericjang/pt-jax
This blog post is a tutorial on implementing path tracing, a physically-based rendering algorithm, in JAX. …
Safety & Alignment
Safety Gym
We’re releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training.