ML Review

DECEMBER 16, 2019

Machine Learning on Graphs becomes a first-class citizen at AI conferences while being not that mysterious as you might have imagined ?. In contrast, hyperbolic algorithms employ Poincare balls and hyperbolic space. So that hyperbolic embeddings can model hierarchies much better AND use less dimensions compared to Euclidean spaces.

Machine Learning 52

Machine Learning Machine Learning Database Algorithm 52

Google Research AI blog

JANUARY 18, 2023

Transform modalities, or translate the world’s information into any language. I will begin with a discussion of language, computer vision, multi-modal models, and generative machine learning models. We want to build more capable machines that partner with people to accomplish a huge variety of tasks. All kinds of tasks.

ML 132

ML ML AI AI 132

Google Research AI blog

NOVEMBER 16, 2022

Posted by Yanqi Zhou, Research Scientist, Google Research, Brain Team The capacity of a neural network to absorb information is limited by the number of its parameters, and as a consequence, finding more effective ways to increase model parameters has become a trend in deep learning research. In sparsely-activated variants of MoE models (e.g.,

Algorithm 78

Algorithm Natural Language Processing Deep Learning Deep Learning 78

Google Research AI blog

FEBRUARY 2, 2023

With the increasing sophistication of the algorithms and hardware in use today and with the scale at which they run, the complexity of the software necessary to carry out day-to-day tasks only increases. An illustration of AllGather-Einsum with 2-way intra-layer model parallelism, proposed in CollectiveEinsum strategy.

ML 72

ML ML Algorithm Machine Learning 72

AWS Machine Learning Blog

SEPTEMBER 6, 2023

Today, we are excited to announce the capability to fine-tune Llama 2 models by Meta using Amazon SageMaker JumpStart. The Llama 2 family of large language models (LLMs) is a collection of pre-trained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters.

ML 97

ML ML Machine Learning Machine Learning 97

Hacker News

FEBRUARY 14, 2023

And the essence of what I’ll say applies just as well to other current “large language models” [LLMs] as to ChatGPT.) And so for essentially everything I show I’ll be able to include explicit Wolfram Language code that you can immediately run on your computer. seems best.

Machine Learning 182

Machine Learning Machine Learning Algorithm Artificial Intelligence 182

Hacker News

FEBRUARY 2, 2023

This is part 2 in a 3-part series about the Second Law: 1. Computational Foundations for the Second Law of Thermodynamics (forthcoming) 2. A 50-Year Quest: My Personal Journey with the Second Law of Thermodynamics 3. How Did We Get Here? It wasn’t like anything I’d seen before. I programmed in assembler, with my programs on paper tape.

Machine Learning 156

Machine Learning Machine Learning Algorithm Analytics 156

Flipboard

MARCH 26, 2023

Image by SGA How will AI Impact Architecture & Design? As someone who loves to discover and invent new technologies, the incorporation of AI into the architecture, engineering and construction (AEC) field has fascinated me for some time now.

AI 81

AI AI Machine Learning Machine Learning 81