How well do Deep Neural Networks model Human Vision?
نویسندگان
چکیده
منابع مشابه
Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision
Humans can recognize objects in a way that is invariant to scale, translation, and clutter. We use invariance theory as a conceptual basis, to computationally model this phenomenon. This theory discusses the role of eccentricity in human visual processing, and is a generalization of feedforward convolutional neural networks (CNNs). Our model explains some key psychophysical observations relatin...
متن کاملDo Deep Neural Networks Suffer from Crowding?
Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed close to it. In this work, we study the effect of crowding in artificial Deep Neural Networks for object recognition. We analyze both standard deep convolutional neural networks (DCNNs) as well as a new version of DCNN...
متن کاملHow to Construct Deep Recurrent Neural Networks
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a deep RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points of an RNN which may be made deeper; (1) input-to-hidden function, (2) hidden-tohidden ...
متن کاملHow Do Neural Networks Overcome Label Noise?
This work provides an analytical expression for the effect of label noise on the performance of deep neural networks. (a) 5 of MNIST’s 10 classes, with clean labels (b) 20% Random Noise, 100% Network Prediction Accuracy (c) 20% Randomly Spread Flip Noise, 100% Accuracy (d) 20% Locally Concentrated Noise, 80% Accuracy Figure 1: Different types of random label noise. DNNs are extremely resistant ...
متن کاملOn Vectorization of Deep Convolutional Neural Networks for Vision Tasks
We recently have witnessed many ground-breaking results in machine learning and computer vision, generated by using deep convolutional neural networks (CNN). While the success mainly stems from the large volume of training data and the deep network architectures, the vector processing hardware (e.g. GPU) undisputedly plays a vital role in modern CNN implementations to support massive computatio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Vision
سال: 2016
ISSN: 1534-7362
DOI: 10.1167/16.12.176