or subscribe with
Join 3,800+ readers for one email each week.
Digests » 169
Want to give back to the community while having a low-key side hustle ($90-$180/hr) to fund your habit? Wynter is looking for professionals to join its research panel. Take industry surveys, be compensated every time you do it. Takes ~10-15 min to be part of one test, super low-key time commitment.
this week's favorite
This document gives a concise outline of some of the common mistakes that occur when using machine learning techniques, and what can be done to avoid them. It is intended primarily as a guide for research students, and focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results.
Utilizing recent advances in machine learning, we introduce a systematic approach to characterize neurons’ input/output (I/O) mapping complexity. Deep neural networks (DNNs) were trained to faithfully replicate the I/O function of various biophysical models of cortical neurons at millisecond (spiking) resolution.
CLIP is a model released by OpenAI earlier this year. It was trained to learn “visual concepts from natural language supervision” on more than 400 million image-text pairs using an impressive amount of compute (256 GPUs for 2 weeks).
Introducing the latest album by the versatile metal genius DeepSlayerXL, with song reviews by GPT-3. *Apologies to ML researchers for saying “AI” in the title, the article was written for a general audience.
I just sat down this morning and organized all deep learning related videos I recorded in 2021. I am sure this will be a useful reference for my future self, but I am also hoping it might be useful for one or the other person out there.