MACHINE LEARNING

ConvNets computational efficiency compared to 2007 object recognition models

By

–

03 December 2023 11h02

Not true. ConvNets were actually relatively cheap compared to the dominant models of object recognition circa 2007.
They were much smaller than current architectures, of course.

Academic AI Course Ahead of Industry Trends

By

–

03 December 2023 10h47

One case where an academic course was ahead of industry trends Now in my course, I talk about SSL, energy-based models, and JEPA….

FAIR’s Scientific Breakthroughs and Open-Source Impact

By

–

03 December 2023 10h16

You seem extremely misinformed.
FAIR has *simultaneously* produced scientific breakthroughs, insanely popular open-source packages, libraries, and platforms (e.g. PyTorch), *and* had an *enormous* impact on the company.
Lots of technologies originally developed at FAIR made their

→ View original post on X — @miketamir

ZipLoRA: Efficient Parameter-Efficient Fine-Tuning for Large Language Models

By

@miketamir

–

03 December 2023 3h01

ZipLoRA https://
bit.ly/46s765G
#AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @fofrai

Neo Learning Kung Fu with LoRA Fine-tuning Technique

By

@fofrai

–

02 December 2023 21h18

I bet when Neo learns Kung Fu he’s using a lora.

→ View original post on X — @miketamir

Learning JAX as a PyTorch Developer Guide

By

@miketamir

–

02 December 2023 21h01

Learning JAX as a PyTorch developer https://
bit.ly/49Vz1Os
#AI #MachineLearning #DeepLearning #LLMs #DataScience

ConvNets Early Debates: Computer Vision Community’s Intellectual Journey

By

–

02 December 2023 19h51

Haha!
It wasn't quite like that.
Many senior members of the CV community were actually very friendly and curious about ConvNets (if skeptical).
There was a true intellectual debate.
Everyone had to have a "theory" of how vision worked.
For me, it was end-to-end gradient-based

→ View original post on X — @montreal_ai

AI Power Consumption and Deployment Cost Analysis

By

@montreal_ai

–

02 December 2023 19h16

Power Hungry Processing: Watts Driving the Cost of AI Deployment? Luccioni et al.: https://
arxiv.org/abs/2311.16863 #ArtificialIntelligence #ClimateAI #MachineLearning