deep neural network

by Synced 2021-04-29 4

Toward a New Generation of Neuromorphic Computing: IBM & ETH Zurich’s Biologically Inspired Optimizer Boosts FCNN and SNN Training

IBM and ETH Zurich researchers make progress in reconciling neurophysiological insights with machine intelligence, proposing a novel biologically inspired optimizer for artificial (ANNs) and spiking neural networks (SNNs) that incorporates synaptic integration principles from biology. GRAPES (Group Responsibility for Adjusting the Propagation of Error Signals) leads to improvements in the training time convergence, accuracy and scalability of ANNs and SNNs.

by Synced 2017-12-19 0

AI Emerging Company United States

Embodying Robots With Intelligence

Engineers have long struggled to teach robots how to perform actions that appear simple by human standards. Former OpenAI research scientist Peter Chen believes the solution is transforming such robots into teachable apprentices.

by Synced 2017-10-23 0

AI Global News Research

AlphaGo Zero: Approaching Perfection

Facebook AI Researcher Yuandong Tian says new AlphaGo Zero paper is destined to be a classic.

by Synced 2017-09-09 1

Research

A Brief Review of FlowNet

Recently, CNNs have been successfully used in estimating optical flow. Compared with traditional methods, these methods achieved a large improvement in quality. Here, we will give a brief review on the following papers.

by Synced 2017-08-16 1

Conference Research

Customer Lifetime Value Prediction Using Embeddings

This paper, presented at the RE-WORK Deep Learning in Retail & Advertising Summit in London, provides a detailed explanation on related work, system architecture, and model improvement with embeddings enabled feature learning.