scholarly journals The ventral visual pathway represents animal appearance over animacy, unlike human behavior and deep neural networks

2017 ◽  
Author(s):  
Stefania Bracci ◽  
Ioannis Kalfas ◽  
Hans Op de Beeck
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Deep Neural Networks ◽  
Activity Patterns ◽  
Object Identification ◽  
Visual Appearance ◽  
Learning History ◽  
Fmri Study ◽  
Object Appearance ◽  
Biased Processing

AbstractRecent studies showed agreement between how the human brain and neural networks represent objects, suggesting that we might start to understand the underlying computations. However, we know that the human brain is prone to biases at many perceptual and cognitive levels, often shaped by learning history and evolutionary constraints. Here we explore one such bias, namely the bias to perceive animacy, and used the performance of neural networks as a benchmark. We performed an fMRI study that dissociated object appearance (how an object looks like) from object category (animate or inanimate) by constructing a stimulus set that includes animate objects (e.g., a cow), typical inanimate objects (e.g., a mug), and, crucially, inanimate objects that look like the animate objects (e.g., a cow-mug). Behavioral judgments and deep neural networks categorized images mainly by animacy, setting all objects (lookalike and inanimate) apart from the animate ones. In contrast, activity patterns in ventral occipitotemporal cortex (VTC) were strongly biased towards object appearance: animals and lookalikes were similarly represented and separated from the inanimate objects. Furthermore, this bias interfered with proper object identification, such as failing to signal that a cow-mug is a mug. The bias in VTC to represent a lookalike as animate was even present when participants performed a task requiring them to report the lookalikes as inanimate. In conclusion, VTC representations, in contrast to neural networks, fail to veridically represent objects when visual appearance is dissociated from animacy, probably due to a biased processing of visual features typical of animate objects.

Representation of adversarial images in deep neural networks and the human brain

2018 ◽  
Author(s):  
Chi Zhang ◽  
Xiaohan Duan ◽  
Ruyuan Zhang ◽  
Li Tong
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Deep Neural Networks

Deep Convolutional Neural Network for Object Classification

2021 ◽  
pp. 317-343
Author(s):  
Amira Ahmad Al-Sharkawy ◽  
Gehan A. Bahgat ◽  
Elsayed E. Hemayed ◽  
Samia Abdel-Razik Mashali
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computational Models ◽  
Human Performance ◽  
Deep Neural Networks ◽  
Object Classification ◽  
Classification Problem ◽  
Deep Convolutional Neural Network ◽  
Object Appearance

Object classification problem is essential in many applications nowadays. Human can easily classify objects in unconstrained environments easily. Classical classification techniques were far away from human performance. Thus, researchers try to mimic the human visual system till they reached the deep neural networks. This chapter gives a review and analysis in the field of the deep convolutional neural network usage in object classification under constrained and unconstrained environment. The chapter gives a brief review on the classical techniques of object classification and the development of bio-inspired computational models from neuroscience till the creation of deep neural networks. A review is given on the constrained environment issues: the hardware computing resources and memory, the object appearance and background, and the training and processing time. Datasets that are used to test the performance are analyzed according to the images environmental conditions, besides the dataset biasing is discussed.

Network attributes describe a similarity between deep neural networks and large scale brain networks

2019 ◽  
Author(s):  
Kosuke Takagi
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Human Brain ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Distribution Model ◽  
Common Mechanism ◽  
Learning Models ◽  
Connection Weight ◽  
Wide Range

Abstract Despite the recent success of deep learning models in solving various problems, their ability is still limited compared with human intelligence, which has the flexibility to adapt to a changing environment. To obtain a model which achieves adaptability to a wide range of problems and tasks is a challenging problem. To achieve this, an issue that must be addressed is identification of the similarities and differences between the human brain and deep neural networks. In this article, inspired by the human flexibility which might suggest the existence of a common mechanism allowing solution of different kinds of tasks, we consider a general learning process in neural networks, on which no specific conditions and constraints are imposed. Subsequently, we theoretically show that, according to the learning progress, the network structure converges to the state, which is characterized by a unique distribution model with respect to network quantities such as the connection weight and node strength. Noting that the empirical data indicate that this state emerges in the large scale network in the human brain, we show that the same state can be reproduced in a simple example of deep learning models. Although further research is needed, our findings provide an insight into the common inherent mechanism underlying the human brain and deep learning. Thus, our findings provide suggestions for designing efficient learning algorithms for solving a wide variety of tasks in the future.

scholarly journals Beyond Core Object Recognition: Recurrent processes account for object recognition under occlusion

2018 ◽  
Author(s):  
Karim Rajaei ◽  
Yalda Mohsenzadeh ◽  
Reza Ebrahimpour ◽  
Seyed-Mahdi Khaligh-Razavi
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Object Recognition ◽  
Human Brain ◽  
Deep Neural Networks ◽  
Temporal Dynamics ◽  
Computational Modelling ◽  
Mechanistic Explanation ◽  
The Core ◽  
Level Performance

AbstractCore object recognition, the ability to rapidly recognize objects despite variations in their appearance, is largely solved through the feedforward processing of visual information. Deep neural networks are shown to achieve human-level performance in these tasks, and explain the primate brain representation. On the other hand, object recognition under more challenging conditions (i.e. beyond the core recognition problem) is less characterized. One such example is object recognition under occlusion. It is unclear to what extent feedforward and recurrent processes contribute in object recognition under occlusion. Furthermore, we do not know whether the conventional deep neural networks, such as AlexNet, which were shown to be successful in solving core object recognition, can perform similarly well in problems that go beyond the core recognition. Here, we characterize neural dynamics of object recognition under occlusion, using magnetoencephalography (MEG), while participants were presented with images of objects with various levels of occlusion. We provide evidence from multivariate analysis of MEG data, behavioral data, and computational modelling, demonstrating an essential role for recurrent processes in object recognition under occlusion. Furthermore, the computational model with local recurrent connections, used here, suggests a mechanistic explanation of how the human brain might be solving this problem.Author SummaryIn recent years, deep-learning-based computer vision algorithms have been able to achieve human-level performance in several object recognition tasks. This has also contributed in our understanding of how our brain may be solving these recognition tasks. However, object recognition under more challenging conditions, such as occlusion, is less characterized. Temporal dynamics of object recognition under occlusion is largely unknown in the human brain. Furthermore, we do not know if the previously successful deep-learning algorithms can similarly achieve human-level performance in these more challenging object recognition tasks. By linking brain data with behavior, and computational modeling, we characterized temporal dynamics of object recognition under occlusion, and proposed a computational mechanism that explains both behavioral and the neural data in humans. This provides a plausible mechanistic explanation for how our brain might be solving object recognition under more challenging conditions.

scholarly journals Topological Augmentation of Latent Information Streams in Feed-Forward Neural Networks

2020 ◽  
Author(s):  
James M. Shine ◽  
Mike Li ◽  
Oluwasanmi Koyejo ◽  
Ben Fulcher ◽  
Joseph T. Lizier
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Activity Patterns ◽  
Edge Weight ◽  
Feed Forward ◽  
Information Theoretic ◽  
Systems Neuroscience ◽  
Feed Forward Network ◽  
Low Dimensional

AbstractThe algorithmic rules that define deep neural networks are clearly defined, however the principles that define their performance remain poorly understood. Here, we use systems neuroscience and information theoretic approaches to analyse a feedforward neural network as it is trained to classify handwritten digits. By tracking the topology of the network as it learns, we identify three distinct phases of topological reconfiguration. Each phase brings the connections of the neural network into alignment with patterns of information contained in the input dataset, as well as the preceding layers. Performing dimensionality reduction on the data reveals a process of low-dimensional category separation as a function of learning. Our results enable a systems-level understanding of how deep neural networks function, and provide evidence of how neural networks reorganize edge weights and activity patterns so as to most effectively exploit the information theoretic content of input data during edge-weight training.SummaryTrained neural networks are capable of remarkable performance on complex categorization tasks, however the precise rules according to which the network reconfigures during training remain poorly understood. We used a combination of systems neuroscience and information theoretic analyses to interrogate the network topology of a simple, feed-forward network as it was trained on a digitclassification task. Over the course of training, the hidden layers of the network reconfigured in characteristic ways that were reminiscent of key results in network neuroscience studies of human brain imaging. In addition, we observed a strong correspondence between the topological changes at different learning phases and information theoretic signatures of the data that were entered into the network. In this way, we show how neural networks learn.

scholarly journals Brain-inspired Multimodal Learning Based on Neural Networks

2018 ◽  
Vol 4 (1) ◽  
pp. 61-72 ◽  
Author(s):  
Chang Liu ◽  
Fuchun Sun ◽  
Bo Zhang
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Computational Models ◽  
Deep Neural Networks ◽  
Brain Research ◽  
Visual Signals ◽  
Multimodal Learning ◽  
Image Captioning ◽  
Unified Framework ◽  
Learning Tasks

Modern computational models have leveraged biological advances in human brain research. This study addresses the problem of multimodal learning with the help of brain-inspired models. Specifically, a unified multimodal learning architecture is proposed based on deep neural networks, which are inspired by the biology of the visual cortex of the human brain. This unified framework is validated by two practical multimodal learning tasks: image captioning, involving visual and natural language signals, and visual-haptic fusion, involving haptic and visual signals. Extensive experiments are conducted under the framework, and competitive results are achieved.

scholarly journals Characterization of deep neural network features by decodability from human brain activity

2018 ◽  
Author(s):  
Tomoyasu Horikawa ◽  
Shuntaro C. Aoki ◽  
Mitsuaki Tsukamoto ◽  
Yukiyasu Kamitani
Keyword(s):  
Human Brain ◽  
Deep Neural Networks ◽  
Human Subjects ◽  
Brain Activity ◽  
Activity Patterns ◽  
Human Vision ◽  
Highly Correlated ◽  
Feature Values ◽  
The Brain

AbstractAchievements of near human-level performances in object recognition by deep neural networks (DNNs) have triggered a flood of comparative studies between the brain and DNNs. Using a DNN as a proxy for hierarchical visual representations, our recent study found that human brain activity patterns measured by functional magnetic resonance imaging (fMRI) can be decoded (translated) into DNN feature values given the same inputs. However, not all DNN features are equally decoded, indicating a gap between the DNN and human vision. Here, we present a dataset derived through the DNN feature decoding analyses including fMRI signals of five human subjects during image viewing, decoded feature values of DNNs (AlexNet and VGG19), and decoding accuracies of individual DNN features with their rankings. The decoding accuracies of individual features were highly correlated between subjects, suggesting the systematic differences between the brain and DNNs. We hope the present dataset will contribute to reveal the gap between the brain and DNNs and provide an opportunity to make use of the decoded features for further applications.

scholarly journals Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks

NeuroImage ◽  
2017 ◽  
Vol 153 ◽  
pp. 346-358 ◽  
Author(s):  
Radoslaw Martin Cichy ◽  
Aditya Khosla ◽  
Dimitrios Pantazis ◽  
Aude Oliva
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Deep Neural Networks

scholarly journals Seeking summary statistics that match peripheral visual appearance using naturalistic textures generated by Deep Neural Networks

2016 ◽  
Vol 16 (12) ◽  
pp. 230
Author(s):  
Thomas Wallis ◽  
Alexander Ecker ◽  
Leon Gatys ◽  
Christina Funke ◽  
Felix Wichmann ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Summary Statistics ◽  
Visual Appearance
Sign in / Sign up

Export Citation Format

Share Document