A guiding framework for our responsible development and use of AI, alongside transparency and accountability in our AI development process.

Generated condensed version of https://github.com/mattjj/autodidact - autodidact.py

Sparsity in deep neural networks promises two improvements in computational efficiency, fewer FLOPs spent both to train the network and to perform inference. We find that both may be quantified...

The 2024 Report

'Non-partisan group' Balance on Bloor includes a former PC candidate, donors, and real estate industry players

In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely...

EDS, an HP Company 'Cat Herders'

Conway, professor emerita of electrical engineering and computer science, has died.

Plot in the terminal using braille dots. Contribute to tammoippen/plotille development by creating an account on GitHub.

Zierler: This is David Zierler, oral historian for the American Institute of Physics. It is April 17, 2020, and it is my great pleasure to be here with Professor N. David Mermin. Dr. Mermin, thank you...

aider is AI pair programming in your terminal

einsum implemented with `itertools.product`. GitHub Gist: instantly share code, notes, and snippets.

In this paper, we explore the idea of training large language models (LLMs) over highly compressed text. While standard subword tokenizers compress text by a small factor, neural text compressors...

Data obtained from a 7-day experience sampling method in a sample of US American users of Twitter (now X) shows short term relationships between Twitter use and wellbeing, sense of belonging, and expe...

Measuring nonlinear feature interaction is an established approach to understanding complex patterns of attribution in many models. In this paper, we use Shapley Taylor interaction indices (STII)...