Security

Using game theory to model poisoning attack scenarios

Poisoning attacks are among the greatest security threats for machine learning (ML) models. In this type of attack, an adversary tries to control a fraction of the data used to train neural networks and injects malicious ...

Computer Sciences

SPFCNN-Miner: A new classifier to tackle class-unbalanced data

Researchers at Chongqing University in China have recently developed a cost-sensitive meta-learning classifier that can be used when the training data available is high-dimensional or limited. Their classifier, called SPFCNN-Miner, ...

Robotics

Applying active inference body perception to a humanoid robot

A key challenge for robotics researchers is developing systems that can interact with humans and their surrounding environment in situations that involve varying degrees of uncertainty. In fact, while humans can continuously ...

Computer Sciences

Spintronic memory cells for neural networks

In recent years, researchers have proposed a wide variety of hardware implementations for feed-forward artificial neural networks. These implementations include three key components: a dot-product engine that can compute ...

Engineering

Teaching AI agents navigation subroutines by feeding them videos

Researchers at UC Berkeley and Facebook AI Research have recently proposed a new approach that can enhance the navigation skills of machine learning models. Their method, presented in a paper pre-published on arXiv, allows ...

Machine Learning & AI

A new approach for unsupervised paraphrasing without translation

In recent years, researchers have been trying to develop methods for automatic paraphrasing, which essentially entails the automated abstraction of semantic content from text. So far, approaches that rely on machine translation ...

Machine Learning & AI

Researchers try to recreate human-like thinking in machines

Researchers at Oxford University have recently tried to recreate human thinking patterns in machines, using a language guided imagination (LGI) network. Their method, outlined in a paper pre-published on arXiv, could inform ...

Robotics

REPLAB: A low-cost benchmark platform for robotic learning

Researchers at UC Berkeley have developed a reproducible, low-cost and compact benchmark platform to evaluate robotic learning approaches, which they called REPLAB. Their recent study, presented in a paper pre-published on ...

page 1 from 5