How Does the Brain Solve Visual Object Recognition?

DiCarlo, James J.; Zoccolan, Davide; Rust, Nicole C.

doi:10.1016/j.neuron.2012.01.010

Cited by 1,497 publications

(1,441 citation statements)

References 187 publications

Supporting

Mentioning

1,278

Contrasting

Unclassified

Order By: Relevance

“…While the visual cortex of BNNs may use quite different learning algorithms, its objective function to be minimised may be quite similar to the one of visual ANNs. In fact, results obtained with relatively deep artificial DBNs (Lee et al, 2007b) and CNNs (Yamins et al, 2013) seem compatible with insights about the visual pathway in the primate cerebral cortex, which has been studied for many decades (e.g., Hubel and Wiesel, 1968;Perrett et al, 1982;Desimone et al, 1984;Felleman and Van Essen, 1991;Perrett et al, 1992;Kobatake and Tanaka, 1994;Logothetis et al, 1995;Bichot et al, 2005;Hung et al, 2005;Lennie and Movshon, 2005;Connor et al, 2007;Kriegeskorte et al, 2008;DiCarlo et al, 2012); compare a computer vision-oriented survey (Kruger et al, 2013).…”

Section: Consequences For Neurosciencementioning

confidence: 81%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.LATEX source: http://www.idsia.ch/˜juergen/DeepLearning8Oct2014.tex Complete BIBTEX file (888 kB): http://www.idsia.ch/˜juergen/deep.bib Preface This is the preprint of an invited Deep Learning (DL) overview. One of its goals is to assign credit to those who contributed to the present state of the art. I acknowledge the limitations of attempting to achieve this goal. The DL research community itself may be viewed as a continually evolving, deep network of scientists who have influenced each other in complex ways. Starting from recent DL results, I tried to trace back the origins of relevant ideas through the past half century and beyond, sometimes using "local search" to follow citations of citations backwards in time. Since not all DL publications properly acknowledge earlier relevant work, additional global search strategies were employed, aided by consulting numerous neural network experts. As a result, the present preprint mostly consists of references. Nevertheless, through an expert selection bias I may have missed important work. A related bias was surely introduced by my special familiarity with the work of my own DL research group in the past quarter-century. For these reasons, this work should be viewed as merely a snapshot of an ongoing credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to juergen@idsia.ch.

show abstract

Section: Consequences For Neurosciencementioning

confidence: 81%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

show abstract

“…This results in an increase in receptive field (RF) size and concurrently an increase in the specificity of tuning (Zeiler & Fergus, 2014). This increase of receptive field size and tuning specificity traversing the layers resemble the general architecture of feed-forward visual representations in the human brain (DiCarlo, Zoccolan, & Rust, 2012;Lamme & Roelfsema, 2000).…”

mentioning

confidence: 88%

Visual pathways from the perspective of cost functions and multi-task deep neural networks

Scholte

Losch

Ramakrishnan

et al. 2018

Cortex

View full text Add to dashboard Cite

Deep learning Cost functions RepresentationsVisual processing a b s t r a c t Vision research has been shaped by the seminal insight that we can understand the higher-tier visual cortex from the perspective of multiple functional pathways with different goals. In this paper, we try to give a computational account of the functional organization of this system by reasoning from the perspective of multi-task deep neural networks. Machine learning has shown that tasks become easier to solve when they are decomposed into subtasks with their own cost function. We hypothesize that the visual system optimizes multiple cost functions of unrelated tasks and this causes the emergence of a ventral pathway dedicated to vision for perception, and a dorsal pathway dedicated to vision for action.To evaluate the functional organization in multi-task deep neural networks, we propose a method that measures the contribution of a unit towards each task, applying it to two networks that have been trained on either two related or two unrelated tasks, using an identical stimulus set. Results show that the network trained on the unrelated tasks shows a decreasing degree of feature representation sharing towards higher-tier layers while the network trained on related tasks uniformly shows high degree of sharing.We conjecture that the method we propose can be used to analyze the anatomical and functional organization of the visual system and beyond. We predict that the degree to which tasks are related is a good descriptor of the degree to which they share downstream cortical-units.

show abstract

“…First, divisive normalization computes outputs that are sensitive to relevant but not irrelevant stimulus dimensions because in discarding information about mean levels of activity it computes representations that are invariant across changes in that mean (Carandini and Heeger, 2012). Therefore it can make a major contribution to solving core problems of invariant object recognition (DiCarlo, Zoccolan and Rust, 2012). Second, amplifying modulation contributes to invariant object recognition by making it context-sensitive.…”

Section: Perceptual Invariance and Adaptive Modification Of Rf Selectmentioning

confidence: 99%

On the functions, mechanisms, and malfunctions of intracortical contextual modulation

Phillips

Clark

Silverstein

2015

Neuroscience & Biobehavioral Reviews

View full text Add to dashboard Cite

A broad neuron-centric conception of contextual modulation is reviewed and re-assessed in the light of recent neurobiological studies of amplification, suppression, and synchronization. Behavioural and computational studies of perceptual and higher cognitive functions that depend on these processes are outlined, and evidence that those functions and their neuronal mechanisms are impaired in schizophrenia is summarized. Finally, we compare and assess the long-term biological functions of contextual modulation at the level of computational theory as formalized by the theories of coherent infomax and free energy reduction. We conclude that those theories, together with the many empirical findings reviewed, show how contextual modulation at the neuronal level enables the cortex to flexibly adapt the use of its knowledge to current circumstances by amplifying and grouping relevant activities and by suppressing irrelevant activities.

show abstract

How Does the Brain Solve Visual Object Recognition?

Cited by 1,497 publications

References 187 publications

Deep learning in neural networks: An overview

Deep learning in neural networks: An overview

Visual pathways from the perspective of cost functions and multi-task deep neural networks

On the functions, mechanisms, and malfunctions of intracortical contextual modulation

Contact Info

Product

Resources

About