PhD Student in Computer Science, University of Miami
Machine Learning, Artificial Intelligence and Computational Neuroscience
Visual system of our brain is very accurate and sophisticated to recognize objects correctly. We still can detect and understand the objects in situations where objects are partially visible, occluded, or even in poorly lighting condition. The same is not this easy when it comes to computer to recognize objects. But, these days, some machine learning models based on artificial neural networks, called convolutional neural networks (CNNs), are proved to be a very good model for the computer to recognize objects. What makes our brain and the CNNs such a good model for object detection? Are there any similarities, if any, between the two? Goal of my research is to pursue these long standing questions researchers are trying to answer, and uncover the similarities between artificial and biological neurons. We already have some results on various metrics that there are some qualitative correspondence between the two.
Abstract: From linear classifiers to neural networks, image classification has been a widely explored topic in mathematics, and many algorithms have proven to be effective classifiers. However, the most accurate classifiers typically have significantly high storage costs, or require complicated procedures that may be computationally expensive. We present a novel (nonlinear) classification approach using truncation of local tensor singular value decompositions (tSVD) that robustly offers accurate results, while maintaining manageable storage costs. Our approach takes advantage of the optimality of the representation under the tensor algebra described to determine to which class an image belongs. We extend our approach to a method that can determine specific pairwise match scores, which could be useful in, for example, object recognition problems where pose/position are different. We demonstrate the promise of our new techniques on the MNIST data set.
Pub.: 29 Jun '17, Pinned: 30 Jun '17
Abstract: Fueled by innovation in the computer vision and artificial intelligence communities, recent developments in computational neuroscience have used goal-driven hierarchical convolutional neural networks (HCNNs) to make strides in modeling neural single-unit and population responses in higher visual cortical areas. In this Perspective, we review the recent progress in a broader modeling context and describe some of the key technical innovations that have supported it. We then outline how the goal-driven HCNN approach can be used to delve even more deeply into understanding the development and organization of sensory cortical processing.
Pub.: 23 Feb '16, Pinned: 30 Jun '17
Abstract: Understanding how biological visual systems recognize objects is one of the ultimate goals in computational neuroscience. From the computational viewpoint of learning, different recognition tasks, such as categorization and identification, are similar, representing different trade-offs between specificity and invariance. Thus, the different tasks do not require different classes of models. We briefly review some recent trends in computational vision and then focus on feedforward, view-based models that are supported by psychophysical and physiological data.
Pub.: 29 Dec '00, Pinned: 30 Jun '17