OPTIMIZATION | Synced

by Synced 2021-11-05 2

Google & UC Berkeley’s Data-Driven Offline Optimization Approach Significantly Boosts Hardware Accelerator Performance, Reduces Simulation Time by More Than 90%

A research team from Google Research and UC Berkeley proposes PRIME, an offline data-driven approach that can architect hardware accelerators without any form of simulations. Compared to state-of-the-art simulation-driven methods, PRIME achieves impressive performance improvements of up to 1.54× while reducing the total required simulation time by up to 99 percent.

by Synced 2021-07-30 2

AI Machine Learning & Data Science Research

Accelerating Quadratic Optimization Up to 3x With Reinforcement Learning

A research team from the University of California, Princeton University and ETH Zurich proposes RLQP, an accelerated QP solver based on operator-splitting QP (OSQP) that uses deep reinforcement learning (RL) to speed up the solver’s convergence rate.

by Synced 2021-06-07 2

AI Machine Learning & Data Science Popular Research

Google Proposes Efficient and Modular Implicit Differentiation for Optimization Problems

A research team from Google Research combines the benefits of implicit differentiation and autodiff and proposes a unified, efficient and modular approach for implicit differentiation of optimization problems.

by Synced 2021-04-02 3

AI Tech Blog

Synced Tradition and Machine Learning Series | Part 3: Optimization Basics – Probabilities and Inference

Probability theory is a mathematical framework for quantifying our uncertainty about the world, and is a fundamental building block in the study of machine learning. The purpose of this article is to provide the vocabulary and mathematics needed before applying probability theory to machine learning tasks.

by Synced 2021-01-23 1

AI Tech Blog

Synced Tradition and Machine Learning Series | Part 2: Optimization Basics

This is the second in a special Synced series of introductory articles on traditionally theoretical fields of studies and their impact on modern-day machine learning.

by Synced 2018-03-10 2

AI

How AI Can Help The Oil Industry

To apply AI technology to the oil and gas industry, oil companies and startups generally first establish either a research group or a research center for the purpose. AI for oil and gas is a huge potential market, expected to reach US$2.85 billion by 2022.

by Synced 2017-05-08 0

Research

Understanding CNN from Signal Perspective

RECOS model supply us with a signal analysis perspective of Convolution Neural Network. From this perspective, we can see the effectiveness of activation and deep architectures.