MATRIX Fall Seminar Series – Dr. Sek Chai

Dynamically Throttleable Neural Networks

Sek Chai, PhD

Chief Technology Officer and Co-Founder

Latent AI

Friday, October 7 2022

11 AM CST – 12 PM CST

Join from the webinar link

https://utsa.webex.com/utsa/j.php?MTID=m432873fd789a104abcb6de4cd4e6bd57

Deep learning model inferences are typically processed with statically defined allocation of compute and memory resources. However, real-world conditions are often varying and thereby, a static runtime inference is neither optimal from an accuracy or efficiency perspective. The problem lies in the current approaches that build model runtime that occupy a single point in the trade-space between performance and resource use. In this presentation, we present a new way to run your neural network dynamically to minimize the working footprint for both memory and compute horsepower. Such an approach enables a runtime that is highly agile, can self-regulate, and could afford new benefits from a robustness perspective.

LINK

MATRIX Fall Seminar Series – Dr. Mark Goldberg

Mapping the Stroke “RE-Connectome”

Mark Goldberg, MD

Professor of Neurology

Associate Vice President for Strategic Research Initiatives

UT Health San Antonio

Friday, September 30, 2022

11 AM CST – 12 PM CST

Join from the webinar link

https://utsa.webex.com/utsa/j.php?MTID=m732b1ddde75e79c34bcb0177fe4e1d57

How can the brain restore its function when parts are irreversibly injured?  Stroke, or “brain attack” occurs when an artery supplying one part of the brain becomes blocked by atherosclerosis or blood clot.  The blockage may resolve spontaneously, or hospital stroke specialists may use drugs or catheters to remove the clot.  But if the artery remains blocked for several hours the tissue will be permanently damaged, and the stroke patient will have deficits that reflect the brain region, such as loss of strength, sensation, vision, speech or memory.   Surprisingly, most stroke patients have at least partial recovery of function over the next 90 days, even though the injured neurons and other brain cells do not regenerate.  This occurs because of neural plasticity, the ability of the nervous system to change its activity in response to intrinsic or extrinsic stimuli by reorganizing its structure, functions, or connections.

Our lab studies a unique form of post-stroke plasticity in a mouse model.   After a targeted injury of the primary motor cortex on one hemisphere, the axons from cortex to spinal cord (corticospinal tract) degenerate and muscle function is impaired.   Within 2-4 weeks, axons from the opposite – uninjured –  corticospinal tract send new collateral sprouts across the spinal cord, where they form synapses that replace the ones lost after stroke.  This is a remarkable form of plasticity because the neurons responsible for repair are far from the location of injury.  Neurons and supporting glial cells activate molecular programs of axon growth that do not normally occur in the adult nervous system.

We’ve developed a microscopy and image analysis pipeline to generate large scale 3D data of the full set of brain and spinal connections that change after injury (which we term the “RE-Connectome”).  Viral vectors and transgenic mice express fluorescent proteins in axons and presynaptic terminals.   Mouse brains and spinal cords are removed and fixed after stroke and imaged using a serial two-photon tomography microscope.  The pipeline for whole brain image analysis includes supervised machine learning (pixel-wise random forest models via the “ilastik” software package) followed by registration to a standardized 3-D atlas of the adult mouse brain or spinal cord.  In this talk, we’ll present some conclusions from our reconnectome data, and review challenges with image segmentation.   This model of nervous system plasticity may provide approaches to promoting resilience in human stroke or in neuromorphic networks.

LINK

MATRIX Fall Seminar Series – Dr. Panagiotis (Panos) Markopoulos

Tensor Methods for Efficient, Robust, and Continual Machine Learning

Dr. Panagiotis (Panos P.) Markopoulos

UTSA

Friday, September 23, 2022

11am – 12pm CST

Abstract: Tensors are data structures that generalize vectors and matrices to arrays of higher order. Similar to matrices, tensors capture and preserve inherent correlations between measurements. For example, an RGB video can be naturally structured as a 4-way tensor such that entries (50,112,3,10) and (50,112,3,11) correspond to the value of the same pixel (50, 112), at the same frequency (B), and successive time frames (10 and 11). Accordingly, over the past decades, tensors have found numerous applications in fields such as signal processing, data mining, machine learning, and computer vision. More recently, the use of tensors has extended to modeling, training, and processing neural network parameters, such as in convolutional filters and fully connected layers. Similar to matrices, tensors are amenable to latent-factor analysis, that can serve multiple purposes, including compression, feature extraction, visualization, and denoising. In this talk, we will focus on deep learning and show how tensor factorization methods have been used for delivering effective solutions for efficient, robust, and continual machine learning.

Join from the webinar link

https://utsa.webex.com/utsa/j.php?MTID=m6b944381e9981692a5f461d1f8d69d39

LINK

MATRIX Fall Seminar Series – Dr. David Anthony

Machine Learning in the Wild: Moving From Laboratories to Deployments

Dr. David Anthony

Southwest Research Institute

Friday, September 16, 2022

11am – 12pm CST

Abstract:

Maturing machine learning technologies, such as convolutional neural networks and transformers, are rapidly being adopted and deployed to real world environments. In this talk, Dr. Anthony will present multiple projects at Southwest Research Institute that are transitioning these technologies from tightly controlled laboratory environments to practical tools used by end users in a variety environments. These projects span multidisciplinary research from markerless motion capture for primates to autonomous robots operating alongside humans. Dr. Anthony will discuss lessons learned from these example projects as well as practical guidelines for addressing the real-world challenges of applied artificial intelligence.

Join from the webinar link:

https://utsa.webex.com/utsa/j.php?MTID=m310026ac9904c080e69faae800cfbc79

LINK

MATRIX Fall Seminar Series – Dr. Fidel Santamaria

Fractional-order neuronal dynamics: from synapses to memcapacitors

Dr. Fidel Santmaria

UTSA

Friday, September 9, 2022

11am – 12pm CST

Abstract: I will summarize our efforts to generate a unified theoretical effort to study history dependent processes in the nervous system. I will show that the natural mathematical language to study such processes are fractional order differential equations, particularly applied to reaction diffusion. After a few examples from synapses to whole neurons, I will introduce our efforts to implement analog circtuits with fractional order dynamics. This will take us to the use of memristors and how these circuits could perform optimal coding of natural signals.

Join from the webinar link:

https://utsa.webex.com/utsa/j.php?MTID=me082d690bf67403dd8ea96e8981c0cd6

LINK

MATRIX Fall Seminar Series – Dr. Yulia Sandamirskaya

Neuromorphic computing: from theory to applications of brain-inspired AI

Dr. Yulia Sandamirskaya

Intel

Friday, September 2, 2022

11 AM – 12 PM CST

LINK