scholarly journals Do deep neural networks see the way we do?

2019 ◽  
Author(s):  
Georgin Jacob ◽  
R. T. Pramod ◽  
Harish Katti ◽  
S. P. Arun
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Relative Size ◽  
Training Data ◽  
Object Representations ◽  
Multiple Dimensions ◽  
Deep Networks ◽  
The Brain ◽  
Global Advantage ◽  
The Way

ABSTRACTDeep neural networks have revolutionized computer vision, and their object representations match coarsely with the brain. As a result, it is widely believed that any fine scale differences between deep networks and brains can be fixed with increased training data or minor changes in architecture. But what if there are qualitative differences between brains and deep networks? Do deep networks even see the way we do? To answer this question, we chose a deep neural network optimized for object recognition and asked whether it exhibits well-known perceptual and neural phenomena despite not being explicitly trained to do so. To our surprise, many phenomena were present in the network, including the Thatcher effect, mirror confusion, Weber’s law, relative size, multiple object normalization and sparse coding along multiple dimensions. However, some perceptual phenomena were notably absent, including processing of 3D shape, patterns on surfaces, occlusion, natural parts and a global advantage. Our results elucidate the computational challenges of vision by showing that learning to recognize objects suffices to produce some perceptual phenomena but not others and reveal the perceptual properties that could be incorporated into deep networks to improve their performance.

scholarly journals Qualitative similarities and differences in visual object representations between brains and deep networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Georgin Jacob ◽  
R. T. Pramod ◽  
Harish Katti ◽  
S. P. Arun
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Deep Neural Networks ◽  
Relative Size ◽  
Sufficient Conditions ◽  
Human Perception ◽  
Visual Object ◽  
Object Representations ◽  
Deep Networks ◽  
Global Advantage

AbstractDeep neural networks have revolutionized computer vision, and their object representations across layers match coarsely with visual cortical areas in the brain. However, whether these representations exhibit qualitative patterns seen in human perception or brain representations remains unresolved. Here, we recast well-known perceptual and neural phenomena in terms of distance comparisons, and ask whether they are present in feedforward deep neural networks trained for object recognition. Some phenomena were present in randomly initialized networks, such as the global advantage effect, sparseness, and relative size. Many others were present after object recognition training, such as the Thatcher effect, mirror confusion, Weber’s law, relative size, multiple object normalization and correlated sparseness. Yet other phenomena were absent in trained networks, such as 3D shape processing, surface invariance, occlusion, natural parts and the global advantage. These findings indicate sufficient conditions for the emergence of these phenomena in brains and deep networks, and offer clues to the properties that could be incorporated to improve deep networks.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals Brain hierarchy score: Which deep neural networks are hierarchically brain-like?

2020 ◽  
Author(s):  
Soma Nonaka ◽  
Kei Majima ◽  
Shuntaro C. Aoki ◽  
Yukiyasu Kamitani
Keyword(s):  
Neural Networks ◽  
Image Recognition ◽  
High Performance ◽  
Deep Neural Networks ◽  
Recognition Performance ◽  
Brain Activity ◽  
Spatial Integration ◽  
Hierarchical Processing ◽  
Visual Areas ◽  
The Brain

SummaryAchievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on the decoding of individual DNN unit activations from human brain activity. We find that BH scores for 29 pretrained DNNs with varying architectures are negatively correlated with image recognition performance, indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that relatively simple feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method provides new ways for designing DNNs and understanding the brain in consideration of their representational homology.

Worshiping Computers

2019 ◽  
pp. 85-110
Author(s):  
Gary Smith ◽  
Jay Cordes
Keyword(s):  
Neural Networks ◽  
Monte Carlo ◽  
Monte Carlo Simulations ◽  
Common Sense ◽  
Deep Neural Networks ◽  
Computer Software ◽  
Square Roots ◽  
The World ◽  
The Way

Computer software, particularly deep neural networks and Monte Carlo simulations, are extremely useful for the specific tasks that they have been designed to do, and they will get even better, much better. However, we should not assume that computers are smarter than us just because they can tell us the first 2000 digits of pi or show us a street map of every city in the world. One of the paradoxical things about computers is that they can excel at things that humans consider difficult (like calculating square roots) while failing at things that humans consider easy (like recognizing stop signs). They can’t pass simple tests like the Winograd Schema Challenge because they do not understand the world the way humans do. They have neither common sense nor wisdom. They are our tools, not our masters.

scholarly journals Syntactic Structure from Deep Learning

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Tal Linzen ◽  
Marco Baroni
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Machine Translation ◽  
Online Publication ◽  
Deep Neural Networks ◽  
Syntactic Structure ◽  
Annual Review ◽  
Publication Date ◽  
Grammatical Knowledge ◽  
Deep Networks

Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation. This success has sparked interest in probing whether these models are inducing human-like grammatical knowledge from the raw data they are exposed to and, consequently, whether they can shed new light on long-standing debates concerning the innate structure necessary for language acquisition. In this article, we survey representative studies of the syntactic abilities of deep networks and discuss the broader implications that this work has for theoretical linguistics. Expected final online publication date for the Annual Review of Linguistics, Volume 7 is January 14, 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

scholarly journals Lessons From Deep Neural Networks for Studying the Coding Principles of Biological Neural Networks

2021 ◽  
Vol 14 ◽  
Author(s):  
Hyojin Bae ◽  
Sang Jeong Kim ◽  
Chang-Eop Kim
Keyword(s):  
Neural Networks ◽  
Neural Coding ◽  
Deep Neural Networks ◽  
Neural Response ◽  
Feature Representation ◽  
Network Feature ◽  
Biological Neural Networks ◽  
Stimulus Features ◽  
The Comparative Study ◽  
The Brain

One of the central goals in systems neuroscience is to understand how information is encoded in the brain, and the standard approach is to identify the relation between a stimulus and a neural response. However, the feature of a stimulus is typically defined by the researcher's hypothesis, which may cause biases in the research conclusion. To demonstrate potential biases, we simulate four likely scenarios using deep neural networks trained on the image classification dataset CIFAR-10 and demonstrate the possibility of selecting suboptimal/irrelevant features or overestimating the network feature representation/noise correlation. Additionally, we present studies investigating neural coding principles in biological neural networks to which our points can be applied. This study aims to not only highlight the importance of careful assumptions and interpretations regarding the neural response to stimulus features but also suggest that the comparative study between deep and biological neural networks from the perspective of machine learning can be an effective strategy for understanding the coding principles of the brain.

scholarly journals Redes de neurônios

1992 ◽  
Vol 14 (14) ◽  
pp. 07
Author(s):  
Rita M. C. de Almeida
Keyword(s):  
Neural Networks ◽  
Spin Glass ◽  
Physical Problem ◽  
Information Storage ◽  
Hopfield Model ◽  
The Brain ◽  
Scientific Advances ◽  
The Way

In the last ten years many scientific advances regarding neurons and the way they are interconnected has mad o it possible to study the dynamics of storage and Processing of information in the brain. In particular, the physicist J. J. Hopfield proposed a formal minimalist model to these neural networks reducing the problem to a particular case of a well – defined physical problem – the spin glass. Although the problem í s well defined, its solution is far from being trivial.Here we introduce the problem, describe Hopfield model, with its achievements and limitations, and present our contribution to the description of information storage in neural networks.

Sign in / Sign up

Export Citation Format

Share Document