Postdoctoral researcher Computer Science, University of Miami
Study divisive normalization as relevant operation in neural processing (natural and artificial).
I currently work on computational models to understand contextual processing in the brain, how neuron responses are the result of interaction of a group rather than individually driven. Focused on the problem of vision, I investigate representations that take into account spatial and temporal contexts and also the influences of attention and the particular task; all within the processing levels of the cortical hierarchy. My broad research interests are machine learning and information theory and their applications to computational neuroscience, signal processing, and computer vision.
Abstract: Normalization techniques have only recently begun to be exploited in supervised learning tasks. Batch normalization exploits mini-batch statistics to normalize the activations. This was shown to speed up training and result in better models. However its success has been very limited when dealing with recurrent neural networks. On the other hand, layer normalization normalizes the activations across all activities within a layer. This was shown to work well in the recurrent setting. In this paper we propose a unified view of normalization techniques, as forms of divisive normalization, which includes layer and batch normalization as special cases. Our second contribution is the finding that a small modification to these normalization schemes, in conjunction with a sparse regularizer on the activations, leads to significant benefits over standard normalization techniques. We demonstrate the effectiveness of our unified divisive normalization framework in the context of convolutional neural nets and recurrent neural networks, showing improvements over baselines in image classification, language modeling as well as super-resolution.
Pub.: 14 Nov '16, Pinned: 30 Jun '17
Abstract: There is increasing evidence that the brain relies on a set of canonical neural computations, repeating them across brain regions and modalities to apply similar operations to different problems. A promising candidate for such a computation is normalization, in which the responses of neurons are divided by a common factor that typically includes the summed activity of a pool of neurons. Normalization was developed to explain responses in the primary visual cortex and is now thought to operate throughout the visual system, and in many other sensory modalities and brain regions. Normalization may underlie operations such as the representation of odours, the modulatory effects of visual attention, the encoding of value and the integration of multisensory information. Its presence in such a diversity of neural systems in multiple species, from invertebrates to mammals, suggests that it serves as a canonical neural computation.
Pub.: 24 Nov '11, Pinned: 30 Jun '17
Abstract: The first two areas of the primate visual cortex (V1, V2) provide a paradigmatic example of hierarchical computation in the brain. However, neither the functional properties of V2 nor the interactions between the two areas are well understood. One key aspect is that the statistics of the inputs received by V2 depend on the nonlinear response properties of V1. Here, we focused on divisive normalization, a canonical nonlinear computation that is observed in many neural areas and modalities. We simulated V1 responses with (and without) different forms of surround normalization derived from statistical models of natural scenes, including canonical normalization and a statistically optimal extension that accounted for image nonhomogeneities. The statistics of the V1 population responses differed markedly across models. We then addressed how V2 receptive fields pool the responses of V1 model units with different tuning. We assumed this is achieved by learning without supervision a linear representation that removes correlations, which could be accomplished with principal component analysis. This approach revealed V2-like feature selectivity when we used the optimal normalization and, to a lesser extent, the canonical one but not in the absence of both. We compared the resulting two-stage models on two perceptual tasks; while models encompassing V1 surround normalization performed better at object recognition, only statistically optimal normalization provided systematic advantages in a task more closely matched to midlevel vision, namely figure/ground judgment. Our results suggest that experiments probing midlevel areas might benefit from using stimuli designed to engage the computations that characterize V1 optimality.
Pub.: 17 Jul '13, Pinned: 30 Jun '17