Deep Leanring | Synced

by Synced 2024-08-26 2

Open Sparse Autoencoders Everywhere: The Ambitious Vision of DeepMind’s Gemma Scope

In a new paper Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2, a Google DeepMind research team introduces Gemma Scope, a comprehensive suite of JumpReLU SAEs.

by Synced 2022-01-20 0

AI Machine Learning & Data Science Research

Meet Hyper-Tune: New SOTA Efficient Distributed Automatic Hyperparameter Tuning at Scale

A research team from Peking University, ETH Zürich and Kuaishou Technology proposes Hyper-Tune, an efficient and robust distributed hyperparameter-tuning framework that features system optimizations such as automatic resource allocation, asynchronous scheduling and a multi-fidelity optimizer, and achieves state-of-the-art performance on multiple tuning tasks.

by Synced 2019-12-20 0

AI Conference Research

ICLR 2020 Accepted Papers Announced

The ICLR 2020 conference programme chairs finally put the selection process behind them, announcing 687 out of 2594 papers had made it to ICLR 2020 — a 26.5 percent acceptance rate.

by Synced 2019-08-05 4

AI Research

Harvard Researchers Benchmark TPU, GPU & CPU for Deep Learning

Because training deep learning models requires intensive computation, AI researchers are always on the lookout for new and better hardware and software platforms for their increasingly sophisticated models.