Top news of the week: 27.04.2021.
Research
Object detection
In this tutorial, you'll use machine learning to build a system that can recognize and track multiple objects in your house through a camera - a task known as object detection. Adding sight ...
(EPSRC DTP) Explainable AI for Multimodal Data Integration in Biomedical Applications
PhD Project - (EPSRC DTP) Explainable AI for Multimodal Data Integration in Biomedical Applications at The University of Manchester, listed on FindAPhD.com
Cerebras Unveils Wafer Scale Engine Two (WSE2): 2.6 Trillion Transistors, 100% Yield
For Cerebras’ first generation WSE is sold as a complete system called CS-1, and the company has several dozen customers with deployed systems up and running, including a number …
Evolving Reinforcement Learning Algorithms
arXiv | ICLR Oral Talk | github | openreview Abstract: We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which ...
ManipulaTHOR training software from AI2 gives virtual robots a hand — and an arm
You can lead a virtual robot to a refrigerator, but you can’t make it pull out a drink. This is the problem that a new robotic agent is designed to address.
Allen School student Victor Zhong named an Apple Scholar for his efforts to teach machines to generalize by reading natural language specifications
“This work is particularly exciting because it opens up new ways to think about how to build more sophisticated language understanding systems with significant less manual …
A.I. reveals the hidden author of a crucial Bible text
Scientists have used machine learning to uncover hidden details in the Dead Sea Scrolls, a crucial Biblical text, such as how many authors the text really had.
A Learning Theoretic Perspective on Local Explainability
Fig 1: A formal relationship between interpretability and complexity. Going from left to right, we consider increasingly complex functions. As the complexity increases, local linear ...