current members

Previous members

Ehsan Ganjidoost, Ph.D. candidate (Computer Science)
    Topic: Predictive Estimators and Perceptual Feedback Networks

Nolan Shaw, Ph.D. candidate (Computer Science)
    Topic: TBD

Wei Sun, M.Math candidate (Computer Science)
    Topic: Predictive Coder Networks and Adversarial Inputs

Tuan Bui, M.Math candidate (Computational Mathematics)
    Topic: Computational Finance and Economics

Evangelia Kryoneriti, Ph.D. candidate (Computer Science),
    Topic: TBD

Alex van de Kleut, M.Math candidate (Computer Science)
    Topic: TBD

Brian Cechmanek, M.Math candidate (Computer Science)
    Topic: TBD

Franky Sun, M.Eng. candidate (Univ. of Jinan, School of Information Science and Engineering)
    Co-supervised by Prof. Lin Wang, U. Jinan
    Topic: Human-Supervised Optimization

Jeremy Zheng, M.Eng. candidate (Univ. of Jinan, School of Information Science and Engineering)
    Co-supervised by Prof. Bo Yang and Prof. Lin Wang, U. Jinan
    Topic: Neural Learning and Co-Evolution

Nolan Shaw, M.Math (Computer Science), Fall 2019
    Topic: The Computational Advantages of Intrinsic Plasticity in Neural Networks

Neil Liu, Undergrad RA (Computer Science)
    Topic: Predictive Coder Networks

Mike Bian, Undergrad RA (Computer Science), Fall 2018
    Topic: Bidirectional Equilibrium Propagation

Ronak Predeep, Undergrad RA (Computer Science), Fall 2018
    Topic: High-Performance Neural Network Implementations


Ahmed Khan, M.Math (Computer Science), 2018

  1. Topic: Bidirectional Learning in Recurrent Neural Networks Using Equilibrium Propagation


Rey Wiyatno, Undergrad RA (Mechatronics Eng), Fall 2017
    Topic: Style Memory in Neural Networks


Louis Castricato, Undergrad RA (Computer Science), Spring 2017

    Topic: Combatting Adversarial Inputs using a Predictive-Estimator Network


Paulo Pacheco, Ph.D. candidate (Computer Science)
    Topic: Interpretability of Neural Representations


Dong Wang, Visiting Scholar
    Assistant Professor, University of Jinan, China
    Topic: Nonlinear Neuron Models


Eric Hunsberger, Ph.D. (Systems Design Engineering), 2017
    (Co-supervised with Chris Eliasmith, Systems Design Engineering)
    Topic: Spiking Deep Neural Networks
   

Peng Wu, Visiting Scholar, Feb-July 2017
    Assistant Professor, University of Jinan, China
    Topic: Flexible Neural Trees with Spiking Neurons


Oscar Yeung (Co-op student), May-Aug 2017
    Topic: Course Content Developer (CS 370)


David Xu, M.Math (Computer Science), 2016

  1. Thesis: Biologically Plausible Neural Learning using Symmetric Predictive Estimators


Andrew Clappison, Summer Research Assistant, April-Aug 2016
    Topic: Symmetric Predictive Coding Networks


Lin Wang, Postdoctoral Fellow, March 2015 - Feb 2016

    Topic: The Evolution of Neural Learning


Cameron Seth, Co-op Undergrad Research Assistant, May-Aug 2015

    Topic: Training Feedback Perception Networks


Shahed Shahir, Ph.D. (Electrical & Computer Engineering), 2015

    (Co-supervised with Safieddin Safavi-Naeini, E&CE)

  1. Thesis: Near-Field Scattering Tomography System for Object Imaging and Material Characterization


Oliver Trujillo, M.Math (Computer Science), 2014

  1. (Co-supervised with Chris Eliasmith, Systems Design Engineering)

  2. Thesis: A Spiking Neural Model of Episodic Memory Encoding and Replay in Hippocampus


Patrick Ji, M.Math (Computer Science), 2014

  1. Thesis: Generalized Strategies for Path Integration using Neural Oscillators


Michael Yang, Undergraduate RA (Computer Science), Sept-Dec 2012

  1. Topic: Neural Oscillators


Yanwei Wang, Ph.D. (Applied Math), 2011

  1. Thesis: Efficient Stockwell Transform with Applications to Image Processing


Michael Lam, M.Math (Computer Science), 2011

  1. Thesis: Retinotopic Preservation in Deep Belief Network Visual Learning


Hwa Young Kim, M.Math (Computer Science), 2009

  1. Thesis: Registering a Non-Rigid Multi-Sensor Ensemble of Images


Maja Omanovic, M.Math (Computer Science), 2006

  1. Thesis: Matching of Dental X-rays for Human Forensic Identification


Alexei Ramotar, M.Math (Computer Science), 2006

  1. Thesis: General Geometry Computed Tomography Reconstruction

We study neural networks and artificial intelligence, with an eye on what we can learn about the brain. Deep neural networks have begun to rival human abilities in perceptual tasks. How do these networks relate to our own perceptual systems, like vision, or audition?


We try to unravel how the brain learns. This pursuit often leads to neural-network learning algorithms that involve feed-back connections and dynamical systems methodologies. The challenge is to train these networks in a deep architecture and investigate how they react to ambiguous stimulus or optical illusions.

(photos)