Phil 1.20.2023

Google’s Deep Learning Tuning Playbook

  • This document is for engineers and researchers (both individuals and teams) interested in maximizing the performance of deep learning models. We assume basic knowledge of machine learning and deep learning concepts.
  • Our emphasis is on the process of hyperparameter tuning. We touch on other aspects of deep learning training, such as pipeline implementation and optimization, but our treatment of those aspects is not intended to be complete.
  • We assume the machine learning problem is a supervised learning problem or something that looks a lot like one (e.g. self-supervised). That said, some of the prescriptions in this document may also apply to other types of problems.

There is a LLM search engine: Perplexity.ai. It’s not bad, and includes pointers to sources. It seems to have good guardrails, too:

Oops. That’s not the Moby Dick that I read:

GPT Agents

  • Start NarrativeExplorer and schema – started!

SBIRs

  • Collect BD-related papers and send to T