Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system. However, these CNNs can be fooled by imperceptibly small, explicitly crafted perturbations, and struggle to recognize objects in corrupted images that are easily recognized by humans. Here, by making comparisons with primate neural data, we first observed that CNN models with a neural hidden layer that better matches primate primary visual cortex (V1) are also more robust to adversarial attacks. Inspired by this observation, we developed VOneNets, a new class of hybrid CNN vision models. Each VOneNet contains a fixed weight neural network front-end that simulates primate V1, called the VOneBlock, followed by a neural network back-end adapted from current CNN vision models. The VOneBlock is based on a classical neuroscientific model of V1: the linear-nonlinear-Poisson model, consisting of a biologically-constrained Gabor filter bank, simple and complex cell nonlinearities, and a V1 neuronal stochasticity generator. After training, VOneNets retain high ImageNet performance, but each is substantially more robust, outperforming the base CNNs and state-of-the-art methods by 18% and 3%, respectively, on a conglomerate benchmark of perturbations comprised of white box adversarial attacks and common image corruptions. Finally, we show that all components of the VOneBlock work in synergy to improve robustness. While current CNN architectures are arguably brain-inspired, the results presented here demonstrate that more precisely mimicking just one stage of the primate visual system leads to new gains in ImageNet-level computer vision applications.

In this article, principles involving the intrinsic, deictic, and extrinsic use of spatial prepositions are examined from linguistic, psychological, and AI approaches. First, I define some important terms. Second, those prepositions which permit intrinsic, deictic, and extrinsic use are specified. Third, I examine how the frame of reference is determined for all three cases. Fourth, I look at ambiguities in the use of prepositions and how they can be resolved.

A new generation of prosthetic limbs which allow the wearer to reach for objects automatically, without thinking – just like a real hand – are to be trialed for the first time. The cutting-edge research was lead by a team at Newcastle University who claim to have developed a prosthetic hand that is able to "see" objects in front of it using a simple Logitech webcam, and respond via software to assess and grasp them. The prosthetic hand is able to see and grasp objects automatically without the need to "think"; just like a real hand, says the University The next-gen prosthetic hand works via a fitted camera which instantaneously takes a picture of the object in front of it, assesses its shape and size and triggers a series of movements in the hand. Bypassing the usual processes which require the user to see the object, physically stimulate the muscles in the arm and trigger a movement in the prosthetic limb, the hand'sees' and reacts in one fluid movement. The Newcastle University research team said it is working with experts at Newcastle upon Tyne Hospitals NHS Foundation Trust to offer the'hands with eyes' to patients at Newcastle's Freeman Hospital.

Introducing the world's first beer brewed by artificial intelligence We've created a premium beer that uses complex machine learning algorithms to improve itself from your feedback. After you've tried one of our four bottled conditioned beers, you can tell our A.I. what you think of it, via our online feedback system. This data is then used by our algorithm to brew the next batch. Because our A.I. is constantly reacting to user feedback, we can brew beer that matches what you want, more quickly than anyone else can. That means we get more data and you get a better, fresher beer.

This book is in The Addison-Wesley Series in Artificial Intelligence. Copyright 1984 by Addison-Wesley Publishing Company, Inc, All rights reserved.