Results 1 - 10
of
60
Learning complex cell invariance from natural videos: A plausibility proof
, 2007
"... ..."
(Show Context)
Deep learning of invariant features via simulated fixations in video
- In NIPS
, 2012
"... We apply salient feature detection and tracking in videos to simulate fixations and smooth pursuit in human vision. With tracked sequences as input, a hierarchical network of modules learns invariant features using a temporal slowness constraint. The network encodes invariance which are increasingly ..."
Abstract
-
Cited by 15 (0 self)
- Add to MetaCart
(Show Context)
We apply salient feature detection and tracking in videos to simulate fixations and smooth pursuit in human vision. With tracked sequences as input, a hierarchical network of modules learns invariant features using a temporal slowness constraint. The network encodes invariance which are increasingly complex with hierarchy. Although learned from videos, our features are spatial instead of spatial-temporal, and well suited for extracting features from still images. We applied our features to four datasets (COIL-100, Caltech 101, STL-10, PubFig), and observe a consistent improvement of 4 % to 5 % in classification accuracy. With this approach, we achieve state-of-the-art recognition accuracy 61 % on STL-10 dataset. 1
Learning Bimodal Structure in Audio-Visual Data
"... A novel model is presented to learn bimodally informative structures from audio-visual signals. The signal is represented as a sparse sum of audio-visual kernels. Each kernel is a bimodal function consisting of synchronous snippets of an audio waveform and a spatio-temporal visual basis function. T ..."
Abstract
-
Cited by 11 (0 self)
- Add to MetaCart
A novel model is presented to learn bimodally informative structures from audio-visual signals. The signal is represented as a sparse sum of audio-visual kernels. Each kernel is a bimodal function consisting of synchronous snippets of an audio waveform and a spatio-temporal visual basis function. To represent an audio-visual signal, the kernels can be positioned independently and arbitrarily in space and time. The proposed algorithm uses unsupervised learning to form dictionaries of bimodal kernels from audio-visual material. The basis functions that emerge during learning capture salient audio-visual data structures. In addition it is demonstrated that the learned dictionary can be used to locate sources of sound in the movie frame. Specifically, in sequences containing two speakers the algorithm can robustly localize a speaker even in the presence of severe acoustic and visual distracters.
Recurrent processing during object recognition
- Front. Psychol
, 2013
"... In the mammalian brain, the retina and LGN compress the visual input into an efficient contrast-coded representation using center-surround contrast filters that are radially symmetric (which can be nicely approximated by the difference of two Gaussians, Enroth-Cugell & Robson, 1966; Young, 1987) ..."
Abstract
-
Cited by 10 (4 self)
- Add to MetaCart
(Show Context)
In the mammalian brain, the retina and LGN compress the visual input into an efficient contrast-coded representation using center-surround contrast filters that are radially symmetric (which can be nicely approximated by the difference of two Gaussians, Enroth-Cugell & Robson, 1966; Young, 1987). Then area V1 encodes orientation and other features building upon this basic contrast-enhanced input. (Hubel & Wiesel, 1962) We compress this chain of filters into a sin-gle step by using oriented Gabor filters, which are defined as a Gaussian-shaped spatial weighting multiplying a planar sine wave oriented in a given direction: g(x, y) = e x2
Computing with Spiking Neuron Networks
"... Abstract Spiking Neuron Networks (SNNs) are often referred to as the 3 rd generation of neural networks. Highly inspired from natural computing in the brain and recent advances in neurosciences, they derive their strength and interest from an accurate modeling of synaptic interactions between neuron ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
Abstract Spiking Neuron Networks (SNNs) are often referred to as the 3 rd generation of neural networks. Highly inspired from natural computing in the brain and recent advances in neurosciences, they derive their strength and interest from an accurate modeling of synaptic interactions between neurons, taking into account the time of spike firing. SNNs overcome the computational power of neural networks made of threshold or sigmoidal units. Based on dynamic event-driven processing, they open up new horizons for developing models with an exponential capacity of memorizing and a strong ability to fast adaptation. Today, the main challenge is to discover efficient learning rules that might take advantage of the specific features of SNNs while keeping the nice properties (general-purpose, easy-to-use, available simulators, etc.) of traditional connectionist models. This chapter relates the history of the “spiking neuron ” in Section 1 and summarizes the most currently-in-use models of neurons and synaptic plasticity in Section 2. The computational power of SNNs is addressed in Section 3 and the problem of learning in networks of spiking neurons is tackled in Section 4, with insights into the tracks currently explored for solving it. Finally, Section 5 discusses application domains, implementation issues and proposes several simulation frameworks.
Memory Retention and Spike-Timing-Dependent Plasticity
, 2008
"... You might find this additional information useful... This article cites 57 articles, 15 of which you can access free at: ..."
Abstract
-
Cited by 5 (2 self)
- Add to MetaCart
You might find this additional information useful... This article cites 57 articles, 15 of which you can access free at:
A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction
, 2010
"... ..."
Rapid Feedforward Computation by Temporal Encoding and Learning With Spiking Neurons
, 2012
"... Abstract — Primates perform remarkably well in cognitive tasks such as pattern recognition. Motivated by recent findings in biological systems, a unified and consistent feedforward system network with a proper encoding scheme and supervised temporal rules is built for solving the pattern recognition ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
(Show Context)
Abstract — Primates perform remarkably well in cognitive tasks such as pattern recognition. Motivated by recent findings in biological systems, a unified and consistent feedforward system network with a proper encoding scheme and supervised temporal rules is built for solving the pattern recognition task. The temporal rules used for processing precise spiking patterns have recently emerged as ways of emulating the brain’s computation from its anatomy and physiology. Most of these rules could be used for recognizing different spatiotemporal patterns. However, there arises the question of whether these temporal rules could be used to recognize real-world stimuli such as images. Furthermore, how the information is represented in the brain still remains unclear. To tackle these problems, a proper encoding method and a unified computational model with consistent and efficient learn-ing rule are proposed. Through encoding, external stimuli are converted into sparse representations, which also have properties of invariance. These temporal patterns are then learned through biologically derived algorithms in the learning layer, followed by the final decision presented through the readout layer. The performance of the model with images of digits from the MNIST database is presented. The results show that the proposed model is capable of recognizing images correctly with a performance comparable to that of current benchmark algorithms. The results also suggest a plausibility proof for a class of feedforward models of rapid and robust recognition in the brain. Index Terms — Pattern recognition, spatiotemporal patterns, spike-timing-dependent plasticity (STDP), spiking neural net-work (SNN), supervised learning, temporal encoding, temporal learning. I.
Unsupervised learning of head pose through spike-timing dependent plasticity
- in Perception in Multimodal Dialogue Systems
, 2008
"... Abstract. We present a biologically inspired model for learning proto-typical representations of head poses. The model employs populations of integrate-and-fire neurons and operates in the temporal domain. Times-to-first spike (latencies) are used to develop a rank-order code, which is invariant to ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
Abstract. We present a biologically inspired model for learning proto-typical representations of head poses. The model employs populations of integrate-and-fire neurons and operates in the temporal domain. Times-to-first spike (latencies) are used to develop a rank-order code, which is invariant to global contrast and brightness changes. Our model consists of 3 layers. In the first layer, populations of Gabor filters are used to ex-tract feature maps from the input image. Filter activities are converted into spike latencies to determine their temporal spike order. In layer 2, intermediate level neurons respond selectively to feature combinations that are statistically significant in the presented image dataset. Synap-tic connectivity between layer 1 and 2 is adapted by a mechanism of spike-timing dependent plasticity (STDP). This mechanism realises an unsupervised Hebbian learning scheme that modifies synaptic weights ac-cording to their timing between pre- and postsynaptic spike. The third layer employs a radial basis function (RBF) classifier to evaluate neural responses from layer 2. Our results show quantitatively that the network performs well in discriminating between 9 different input poses gathered from 200 subjects.
RE: A Review and A
- Proposal, Proceedings of the Third ASERC Workshop on Quantitative and Software Engineering
"... doi: 10.3389/fgene.2012.00071 Inferring genetic interactions via a data-driven second order model ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
doi: 10.3389/fgene.2012.00071 Inferring genetic interactions via a data-driven second order model
