Masoud Ghodrati
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Masoud Ghodrati has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Seyed-Mahdi Khaligh-Razavi
Cognetivity Ltd., London, United Kingdom
6 shared publications Karim Rajaei
School of Cognitive Sciences (SCS), Institute for Research in Fundamental Sciences (IPM), Tehran, Iran
5 shared publications- Saeed Reza Kheradpisheh
Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran
5 shared publications - Timothée Masquelier
CerCo UMR 5549, CNRS – Université Toulouse III
5 shared publications - Mohammad Ganjtabesh
Department of Mathematics, Statistics, and Computer Science - College of Science, University of Tehran, Tehran, Iran
3 shared publications - Nicholas Seow Chiang Price
Monash University, Melbourne, Australia
3 shared publications
Latest Publications
- Open Access
- 1 June 2021
- Published by Elsevier in NeuroImage
- Vol. 233, 117896
Perceptual difficulty modulates the direction of information flow in familiar face recognition
- 1 June 2021
- Published by Elsevier in NeuroImage
- Vol. 233, 117896
Open AccessPerceptual difficulty modulates the direction of information flow in familiar face recognition
- Top Cited Papers
- 1 March 2019
- Published by Elsevier in Neural Networks
- Vol. 111, 47-63
Deep learning in spiking neural networks
- 1 March 2019
- Published by Elsevier in Neural Networks
- Vol. 111, 47-63
Top Cited PapersDeep learning in spiking neural networks
- Open Access
- 26 February 2019
- Published by Springer Nature in Nature Communications
- Vol. 10 (1) , 1-13
Contrast and luminance adaptation alter neuronal coding and perception of stimulus orientation
Sensory systems face a barrage of stimulation that continually changes along multiple dimensions. These simultaneous changes create a formidable problem for the nervous system, as neurons must dynamically encode each stimulus dimension, despite changes in other dimensions. Here, we measured how neurons in visual cortex encode orientation following changes in luminance and contrast, which are critical for visual processing, but nuisance variables in the context of orientation coding. Using information theoretic analysis and population decoding approaches, we find that orientation discriminability is luminance and contrast dependent, changing over time due to firing rate adaptation. We also show that orientation discrimination in human observers changes during adaptation, in a manner consistent with the neuronal data. Our results suggest that adaptation does not maintain information rates per se, but instead acts to keep sensory systems operating within the limited dynamic range afforded by spiking activity, despite a wide range of possible inputs.
- 26 February 2019
- Published by Springer Nature in Nature Communications
- Vol. 10 (1) , 1-13
Open AccessContrast and luminance adaptation alter neuronal coding and perception of stimulus orientation
Sensory systems face a barrage of stimulation that continually changes along multiple dimensions. These simultaneous changes create a formidable problem for the nervous system, as neurons must dynamically encode each stimulus dimension, despite changes in other dimensions. Here, we measured how neurons in visual cortex encode orientation following changes in luminance and contrast, which are critical for visual processing, but nuisance variables in the context of orientation coding. Using information theoretic analysis and population decoding approaches, we find that orientation discriminability is luminance and contrast dependent, changing over time due to firing rate adaptation. We also show that orientation discrimination in human observers changes during adaptation, in a manner consistent with the neuronal data. Our results suggest that adaptation does not maintain information rates per se, but instead acts to keep sensory systems operating within the limited dynamic range afforded by spiking activity, despite a wide range of possible inputs.
- Open Access
Deep Learning in Spiking Neural Networks
In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation. Huge amounts of labeled examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and arguably the only viable option if one wants to understand how the brain computes. SNNs are also more hardware friendly and energy-efficient than ANNs, and are thus appealing for technology, especially for portable devices. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy, but also computational cost and hardware friendliness. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while the SNNs typically require much fewer operations.
Open AccessDeep Learning in Spiking Neural Networks
In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation. Huge amounts of labeled examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and arguably the only viable option if one wants to understand how the brain computes. SNNs are also more hardware friendly and energy-efficient than ANNs, and are thus appealing for technology, especially for portable devices. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy, but also computational cost and hardware friendliness. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while the SNNs typically require much fewer operations.
- Open Access
- 1 September 2017
- Published by Elsevier in Progress in Neurobiology
- Vol. 156, 214-255
Towards building a more complex view of the lateral geniculate nucleus: Recent advances in understanding its role
- 1 September 2017
- Published by Elsevier in Progress in Neurobiology
- Vol. 156, 214-255
Open AccessTowards building a more complex view of the lateral geniculate nucleus: Recent advances in understanding its role
- Open Access
- 9 December 2016
- Published by Frontiers Media SA in Frontiers in Human Neuroscience
- Vol. 10, 630
Low-Level Contrast Statistics of Natural Images Can Modulate the Frequency of Event-Related Potentials (ERP) in Humans
Humans are fast and accurate in categorizing complex natural images. It is, however, unclear what features of visual information are exploited by brain to perceive the images with such speed and accuracy. It has been shown that low-level contrast statistics of natural scenes can explain the variance of amplitude of event-related potentials (ERP) in response to rapidly presented images. In this study, we investigated the effect of these statistics on frequency content of ERPs. We recorded ERPs from human subjects, while they viewed natural images each presented for 70 ms. Our results showed that Weibull contrast statistics, as a biologically plausible model, explained the variance of ERPs the best, compared to other image statistics that we assessed. Our time-frequency analysis revealed a significant correlation between these statistics and ERPs’ power within theta frequency band (~3-7 Hz). This is interesting, as theta band is believed to be involved in context updating and semantic encoding. This correlation became significant at ~110 ms after stimulus onset, and peaked at 138 ms. Our results show that not only the amplitude but also the frequency of neural responses can be modulated with low-level contrast statistics of natural images and highlights their potential role in scene perception.
- 9 December 2016
- Published by Frontiers Media SA in Frontiers in Human Neuroscience
- Vol. 10, 630
Open AccessLow-Level Contrast Statistics of Natural Images Can Modulate the Frequency of Event-Related Potentials (ERP) in Humans
Humans are fast and accurate in categorizing complex natural images. It is, however, unclear what features of visual information are exploited by brain to perceive the images with such speed and accuracy. It has been shown that low-level contrast statistics of natural scenes can explain the variance of amplitude of event-related potentials (ERP) in response to rapidly presented images. In this study, we investigated the effect of these statistics on frequency content of ERPs. We recorded ERPs from human subjects, while they viewed natural images each presented for 70 ms. Our results showed that Weibull contrast statistics, as a biologically plausible model, explained the variance of ERPs the best, compared to other image statistics that we assessed. Our time-frequency analysis revealed a significant correlation between these statistics and ERPs’ power within theta frequency band (~3-7 Hz). This is interesting, as theta band is believed to be involved in context updating and semantic encoding. This correlation became significant at ~110 ms after stimulus onset, and peaked at 138 ms. Our results show that not only the amplitude but also the frequency of neural responses can be modulated with low-level contrast statistics of natural images and highlights their potential role in scene perception.
- 14 September 2016
- Published by Wiley in European Journal of Neuroscience
- Vol. 44 (10) , 2759-2773
Orientation selectivity in rat primary visual cortex emerges earlier with low‐contrast and high‐luminance stimuli
In natural vision, rapid and sustained variations in luminance and contrast change the reliability of information available about a visual scene, and markedly affect both neuronal and behavioural responses. The hallmark property of neurons in primary visual cortex (V1), orientation selectivity, is unaffected by changes in stimulus contrast, but it remains unclear how sustained differences in mean luminance and contrast affect the time‐course of orientation selectivity, and the amount of information that neurons carry about orientation. We used reverse correlation with characterize the temporal dynamics of orientation selectivity in rat V1 neurons under four luminance‐contrast conditions. We show that orientation selectivity and mutual information between neuronal responses and stimulus orientation are invariant to contrast or mean luminance. Critically, the time‐course of the emergence of orientation selectivity was affected by both factors; response latencies were longer for low‐ than high‐luminance gratings, and surprisingly, response latencies were also longer for high‐ than low‐contrast gratings. Modelling suggests that luminance‐modulated changes in feedforward gain, in combination with hyperpolarization caused by high contrasts can account for our physiological data. The hyperpolarization at high contrasts may increase signal‐to‐noise ratios, whereas a more depolarized membrane may lead to greater sensitivity to weak stimuli.
- 14 September 2016
- Published by Wiley in European Journal of Neuroscience
- Vol. 44 (10) , 2759-2773
Orientation selectivity in rat primary visual cortex emerges earlier with low‐contrast and high‐luminance stimuli
In natural vision, rapid and sustained variations in luminance and contrast change the reliability of information available about a visual scene, and markedly affect both neuronal and behavioural responses. The hallmark property of neurons in primary visual cortex (V1), orientation selectivity, is unaffected by changes in stimulus contrast, but it remains unclear how sustained differences in mean luminance and contrast affect the time‐course of orientation selectivity, and the amount of information that neurons carry about orientation. We used reverse correlation with characterize the temporal dynamics of orientation selectivity in rat V1 neurons under four luminance‐contrast conditions. We show that orientation selectivity and mutual information between neuronal responses and stimulus orientation are invariant to contrast or mean luminance. Critically, the time‐course of the emergence of orientation selectivity was affected by both factors; response latencies were longer for low‐ than high‐luminance gratings, and surprisingly, response latencies were also longer for high‐ than low‐contrast gratings. Modelling suggests that luminance‐modulated changes in feedforward gain, in combination with hyperpolarization caused by high contrasts can account for our physiological data. The hyperpolarization at high contrasts may increase signal‐to‐noise ratios, whereas a more depolarized membrane may lead to greater sensitivity to weak stimuli.
- Open Access
- 7 September 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 32672
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
- 7 September 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 32672
Open AccessDeep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
- Open Access
- 31 August 2016
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 10, 92
Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder
View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g. 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth) as well as their magnitude, which we call "variation level". We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group) on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier). This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research.
- 31 August 2016
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 10, 92
Open AccessHumans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder
View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g. 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth) as well as their magnitude, which we call "variation level". We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group) on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier). This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research.
- Open Access
- 26 April 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 25025
A specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans
Converging reports indicate that face images are processed through specialized neural networks in the brain –i.e. face patches in monkeys and the fusiform face area (FFA) in humans. These studies were designed to find out how faces are processed in visual system compared to other objects. Yet, the underlying mechanism of face processing is not completely revealed. Here, we show that a hierarchical computational model, inspired by electrophysiological evidence on face processing in primates, is able to generate representational properties similar to those observed in monkey face patches (posterior, middle and anterior patches). Since the most important goal of sensory neuroscience is linking the neural responses with behavioral outputs, we test whether the proposed model, which is designed to account for neural responses in monkey face patches, is also able to predict well-documented behavioral face phenomena observed in humans. We show that the proposed model satisfies several cognitive face effects such as: composite face effect and the idea of canonical face views. Our model provides insights about the underlying computations that transfer visual information from posterior to anterior face patches.
- 26 April 2016
- Published by Springer Nature in Scientific Reports
- Vol. 6 (1) , 25025
Open AccessA specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans
Converging reports indicate that face images are processed through specialized neural networks in the brain –i.e. face patches in monkeys and the fusiform face area (FFA) in humans. These studies were designed to find out how faces are processed in visual system compared to other objects. Yet, the underlying mechanism of face processing is not completely revealed. Here, we show that a hierarchical computational model, inspired by electrophysiological evidence on face processing in primates, is able to generate representational properties similar to those observed in monkey face patches (posterior, middle and anterior patches). Since the most important goal of sensory neuroscience is linking the neural responses with behavioral outputs, we test whether the proposed model, which is designed to account for neural responses in monkey face patches, is also able to predict well-documented behavioral face phenomena observed in humans. We show that the proposed model satisfies several cognitive face effects such as: composite face effect and the idea of canonical face views. Our model provides insights about the underlying computations that transfer visual information from posterior to anterior face patches.