MACHINE LEARNING - AI Dynamics

Unlocking AI’s Full Potential for Human Intelligence

By

–

02 November 2022 19h11

We're Not Using AI to Its Fullest Human Potential https://
time.com/6227118/eric-s
chmidt-ai-human-intelligence/
… @TIME #AI #MachineLearning #DataScience #BigData #Analytics #100DaysofCode #IoT #serverless #womenwhocode #DigitalTransformation #Robots #Python #TensorFlow #DeepLearning

→ View original post on X — @marcusborba,

2 November 2022

Adaptive Optimizers Should Track True Squared Gradients

By

@id_aa_carmack

–

02 November 2022 18h44

Adaptive optimizers like Adam track the square of the gradient, but what they receive as the gradient is actually the sum of the gradients across the batch. It seems likely that better results at different hyper parameters could be obtained if backward passes emitted true grad^2.

→ View original post on X — @id_aa_carmack,

2 November 2022

Detecting Non-Gaussian Distributions in Machine Learning Models

By

@thegautamkamath

–

02 November 2022 18h29

The easiest way to see this is to fix the mean to be 0 and then observe that the returned value will never be negative. Thus it can't be Gaussian. Definitely not easy to spot.

→ View original post on X — @thegautamkamath,

2 November 2022

Neural Operators and AI for Science Talk at MIT IAIFI

By

@animaanandkumar

–

02 November 2022 17h41

It was great visiting @mit @iaifi_news and give a talk about neural operators and AI for science. You can find my talk here https://
youtu.be/RR5-mYQOb7E?t=
1208
…

→ View original post on X — @animaanandkumar,

2 November 2022

Essential Machine Learning Concepts: 130-Page Cheat Sheet

By

@mit_csail

–

02 November 2022 17h00

READ: 130-page cheat sheet outlining key #MachineLearning concepts: https://
bit.ly/130pgMLsheet
———
#ML #BigData #AI #DeepLearning #Algorithms

→ View original post on X — @mit_csail,

2 November 2022

LLMs Self-Improve: New State-of-the-Art Reasoning Capabilities

By

@cerebras

–

02 November 2022 17h00

We recently read ‘Large Language Models Can Self-Improve,’ which demonstrates how to improve the general reasoning ability of multi-billion parameter models and achieve state-of-the-art performance. Have you read it? Check it out and let us know your thoughts! #ML #AI #LLM

→ View original post on X — @cerebras,

2 November 2022

Scalable AI Ecosystem Across Hybrid Cloud Enterprise

By

@dominodatalab

–

02 November 2022 16h06

Doing AI in a hybrid cloud environment? Need to use GPUs to accelerate ML? Check out Kjell Carlsson's talk TODAY, Nov. 2 from 3:05 – 3:30 CT, “Enabling a Scalable, Future-proof AI Ecosystem Across the Hybrid Cloud Enterprise." #MLOps #IoTWorld

→ View original post on X — @dominodatalab,

2 November 2022

Scikit-learn Algorithm Selection Cheat Sheet Guide

By

@abacusai

–

02 November 2022 16h00

Scikit-learn is one of the most useful and important Python libraries for machine learning. A great cheat sheet that will help you decide which algorithm to use:

→ View original post on X — @abacusai,

2 November 2022