SIPLab
Sensory Information Processing Lab

what we do

Quantitative understanding of brain activity, the resulting complex behaviors, and the effects of therapeutic neuromodulation are grand challenges with the potential for enormous societal impact. Simultaneous advances in neural interfacing and data science have created a remarkable opportunity to reshape the way we think about the brain in health and disease.

Our research focus is in computational neuroengineering, an intersection of data science, neurotechnology and computational modeling that aims to advance the understanding of brain function, the engineering of effective interventions, and the development of intelligent systems.

Our research has a particular focus on exploiting closed-loop interactions between biological and artificial intelligence. While this work spans a diverse set of problem domains, our primary translational focus is on deep brain stimulation for treatment resistant depression. Scholarly activity in the SIPLab also includes qualitative, quantitative and creative work (described elsewhere) that advances our effective public communication about emerging areas such as AI, neurotechnology and neuroethics.

We pursue these objectives using direct and indirect (invasive and non-invasive) methods of integrating engineered systems in closed-loop interactions with biology across scales from single cells to human intelligence. These interactions lead us to new ways to conduct experiments to learn about neural systems, new ways to treat diseases of these systems, and new ways to build machines that learn from the intelligence embodied in these systems. It also often leads to advances in data science algorithms that have applications far beyond the original inspiration.

Technically, we approach this research using tools the core philosophy that high-dimensional data typically has information of interest that is low-dimensional and can be represented geometrically (e.g., linear subspaces, sparsity models, manifolds, and dynamical system attractors). Please see our publications for more information on our current research.

news

O'Shaugnessy defends Ph.D.

Congratulations to Dr. Matt O'Shaugnessy, who defended his Ph.D. theses titled "Causal Methods for Understanding Complex Systems". New approaches to understanding black box machine learning methods, interacting dynamical systems, and the interplay of cultural factors that influence our opinions about AI. Best of luck!

Connor defends Ph.D.

Congratulations to Dr. Marissa Connor, who defended her Ph.D. theses titled "Incorporating Manifold Structure of Natural Variations into Statistical Learning". New algorithms for generative manifold models, helping us understand how biological and artificial intelligence systems can learn the structure of the visual world. Best of luck!

O'Shaugnessy wins scicomm award

Congratulations to Matt O'Shaughnessy, who was awarded a Science ATL Communication Fellowship. Congratulations Matt!

Helbling wins research award

Congratulations to Alec Helbling, who was awarded a President's Undergraduate Research Award (PURA) at GT for the fall supporting his project on "Human Interpretable Search of Variational Autoencoder Latent Spaces" under the mentorship of Matt O'Shaugnessy and Kion Fallah!

Canal defends Ph.D.

Congratulations to Dr. Gregory Canal, who defended his Ph.D. theses titled "Feedback Coding for Efficient Interactive Machine Learning". State of the art algorithms and analysis for human-in-the-loop machine learning algorithms. Best of luck!