scholarly journals Guarding Against Adversarial Attacks using Biologically Inspired Contour Integration

2018 ◽  
Vol 4 (1) ◽  
pp. 3
Author(s):  
Salman Khan ◽  
Alexander Wong ◽  
Bryan Tripp
Keyword(s):  
Contour Integration ◽  
Artificial Vision ◽  
Vision Systems ◽  
High Confidence ◽  
Biologically Inspired ◽  
The Brain

Artificial vision systems are susceptible to adversarial attacks. Smallintentional changes to images can cause these systems to mis-classify with high confidence. The brain has many mechanisms forstrengthening weak or confusing inputs. One such technique, con-tour integration can separate objects from irrelevant background.We show that incorporating contour integration within artificial vi-sual systems can increase their robustness to adversarial attacks.

Striatal dopamine mediates hallucination-like perception in mice

Science ◽  
2021 ◽  
Vol 372 (6537) ◽  
pp. eabf4740
Author(s):  
K. Schmack ◽  
M. Bosc ◽  
T. Ott ◽  
J. F. Sturgill ◽  
A. Kepecs
Keyword(s):  
Psychotic Disorders ◽  
Neural Circuit ◽  
Dopamine Neurons ◽  
Striatal Dopamine ◽  
Model Organisms ◽  
High Confidence ◽  
Optogenetic Stimulation ◽  
The Brain ◽  
Central Symptom ◽  
Stimulation Of

Hallucinations, a central symptom of psychotic disorders, are attributed to excessive dopamine in the brain. However, the neural circuit mechanisms by which dopamine produces hallucinations remain elusive, largely because hallucinations have been challenging to study in model organisms. We developed a task to quantify hallucination-like perception in mice. Hallucination-like percepts, defined as high-confidence false detections, increased after hallucination-related manipulations in mice and correlated with self-reported hallucinations in humans. Hallucination-like percepts were preceded by elevated striatal dopamine levels, could be induced by optogenetic stimulation of mesostriatal dopamine neurons, and could be reversed by the antipsychotic drug haloperidol. These findings reveal a causal role for dopamine-dependent striatal circuits in hallucination-like perception and open new avenues to develop circuit-based treatments for psychotic disorders.

Biologically Inspired Components in Embedded Vision Systems

2018 ◽  
pp. 458-493
Author(s):  
Li-Minn Ang ◽  
Kah Phooi Seng ◽  
Christopher Wing Hong Ngau
Keyword(s):  
Vision System ◽  
Low Complexity ◽  
Human Vision ◽  
Primary Concern ◽  
Resource Constrained ◽  
Vision Systems ◽  
Biologically Inspired ◽  
Embedded Vision ◽  
Field Programmable ◽  
Embedded Vision Systems

Biological vision components like visual attention (VA) algorithms aim to mimic the mechanism of the human vision system. Often VA algorithms are complex and require high computational and memory requirements to be realized. In biologically-inspired vision and embedded systems, the computational capacity and memory resources are of a primary concern. This paper presents a discussion for implementing VA algorithms in embedded vision systems in a resource constrained environment. The authors survey various types of VA algorithms and identify potential techniques which can be implemented in embedded vision systems. Then, they propose a low complexity and low memory VA model based on a well-established mainstream VA model. The proposed model addresses critical factors in terms of algorithm complexity, memory requirements, computational speed, and salience prediction performance to ensure the reliability of the VA in a resource constrained environment. Finally a custom softcore microprocessor-based hardware implementation on a Field-Programmable Gate Array (FPGA) is used to verify the implementation feasibility of the presented model.

Deep Learning: The Good, the Bad, and the Ugly

2019 ◽  
Vol 5 (1) ◽  
pp. 399-426 ◽  
Author(s):  
Thomas Serre
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Machine Vision ◽  
Artificial Vision ◽  
Vision Systems ◽  
Comprehensive Overview ◽  
Biological Vision ◽  
Recent Developments ◽  
Visual Intelligence ◽  
Modern Machine

Artificial vision has often been described as one of the key remaining challenges to be solved before machines can act intelligently. Recent developments in a branch of machine learning known as deep learning have catalyzed impressive gains in machine vision—giving a sense that the problem of vision is getting closer to being solved. The goal of this review is to provide a comprehensive overview of recent deep learning developments and to critically assess actual progress toward achieving human-level visual intelligence. I discuss the implications of the successes and limitations of modern machine vision algorithms for biological vision and the prospect for neuroscience to inform the design of future artificial vision systems.

Correlation between Roughness (Ra) and Fractal Dimension (D) Using Artificial Vision Systems for On-Site Inspection

2018 ◽  
Vol 22 (4) ◽  
Author(s):  
José Gabriel Ayala Landeros ◽  
Victor Manuel Castaño Meneses ◽  
María Blanca Becerra Rodríguez ◽  
Saulo Servín Guzmán ◽  
Sonia Elizabeth Román Flores ◽  
...  
Keyword(s):  
Fractal Dimension ◽  
Artificial Vision ◽  
Vision Systems ◽  
On Site Inspection

The first biologically inspired robots

Robotica ◽  
2003 ◽  
Vol 21 (4) ◽  
pp. 351-363 ◽  
Author(s):  
Owen Holland
Keyword(s):  
Biologically Inspired ◽  
Biologically Inspired Robots ◽  
The Brain

Thie first biologically inspired robots, the famous electromechanical tortoises, were designed and built in 1949 by W. Grey Walter. This paper reviews their origins in Walter's theories of the brain and the nature of life, and uses contemporary unpublished notes and photographs to assess their significance then and now.

scholarly journals Spontaneous generation of innate number sense in untrained deep neural networks

2019 ◽  
Author(s):  
Gwangsu Kim ◽  
Jaeson Jang ◽  
Seungdae Baek ◽  
Min Song ◽  
Se-Bum Paik
Keyword(s):  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Number Sense ◽  
Visual Pathway ◽  
Natural Images ◽  
Spontaneous Generation ◽  
Biologically Inspired ◽  
Weight Variation ◽  
Statistical Variation ◽  
The Brain

AbstractNumber-selective neurons are observed in numerically naïve animals, but it was not understood how this innate function emerges in the brain. Here, we show that neurons tuned to numbers can arise in random feedforward networks, even in the complete absence of learning. Using a biologically inspired deep neural network, we found that number tuning arises in three cases of networks: one trained to non-numerical natural images, one randomized after trained, and one never trained. Number-tuned neurons showed characteristics that were observed in the brain following the Weber-Fechner law. These neurons suddenly vanished when the feedforward weight variation decreased to a certain level. These results suggest that number tuning can develop from the statistical variation of bottom-up projections in the visual pathway, initializing innate number sense.

Biologically-Inspired Models for Attentive Robot Vision

2016 ◽  
pp. 69-98 ◽  
Author(s):  
Amirhossein Jamalian ◽  
Fred H. Hamker
Keyword(s):  
Visual Attention ◽  
Information Flow ◽  
Vision Research ◽  
Vision System ◽  
Robot Vision ◽  
Artificial Vision ◽  
Future Research ◽  
Visual Data ◽  
Biologically Inspired ◽  
Speed Up

A rich stream of visual data enters the cameras of a typical artificial vision system (e.g., a robot) and considering the fact that processing this volume of data in real-rime is almost impossible, a clever mechanism is required to reduce the amount of trivial visual data. Visual Attention might be the solution. The idea is to control the information flow and thus to improve vision by focusing the resources merely on some special aspects instead of the whole visual scene. However, does attention only speed-up processing or can the understanding of human visual attention provide additional guidance for robot vision research? In this chapter, first, some basic concepts of the primate visual system and visual attention are introduced. Afterward, a new taxonomy of biologically-inspired models of attention, particularly those that are used in robotics applications (e.g., in object detection and recognition) is given and finally, future research trends in modelling of visual attention and its applications are highlighted.

Sign in / Sign up

Export Citation Format

Share Document