This is a project based course, focusing on the connection between\u00a0neuroscience and AI technology. The brain is a strong, robust, and highly efficient adaptive controller which seamlessly combines electric bursts and analog chemicals.\u00a0 It is capable of contextual perception, prediction, and generation, with multi-scale and multi-level activity. Many of the large leaps in AI come from the understanding of human\u2019s cognition and animal behavior.\u00a0 The course is a must background for research in the intersection of AI and neuroscience.\u00a0 We will discuss additional learning architectures beyond the famous deep networks, such as Kohonen self-organizing networks, Hopfield memory networks, and networks that change activity by context; involve the most advanced ideas that improve AI including lifelong learning and low-energy analog computing; and further introduce neuroscientific findings to improve future AI – such as neuromodulation, dendritic trees, diversity of components, sequence generations, and multi-objectivity. While the course has some homeworks, a chief part of the grade will come from active participation, project, and presentation.\u00a0<\/p>\n
The course requires successful completion of previous courses in AI and Machine Learning (311, 389 or 589) or permission by teacher.\u00a0Delivery method: Students can come to class or be on the zoom \u2013 both are allowed. Presentations will be in person.<\/p>\n
\u00a0\u00a0<\/p>\n
3 Credits<\/p>\n
Class Hours: Mondays 4-6:30PM, LGRC A104A<\/b><\/p>\n
\u00a0<\/b><\/p>\nSchedule<\/h1>\n
\n\n
\n 1. Single Neuron Models<\/td>\n \u00a0<\/td>\n<\/tr>\n \n February 2<\/td>\n McCulloch & Pittz, Hubert & Wiesel, Learning and Adaptation, Perceptron<\/td>\n<\/tr>\n \n 2. Hierarchical Structures<\/td>\n \u00a0<\/td>\n<\/tr>\n \n February 9<\/td>\n Sensory Hierarchies (e.g. visual), Backpropagation Learning<\/td>\n<\/tr>\n \n February 16<\/td>\n Holiday – President’s Day<\/td>\n<\/tr>\n \n February 19<\/td>\n Forward Propagation Learning, Generalized Hierarchies for Abstraction and Generalization<\/td>\n<\/tr>\n \n February 23<\/td>\n Generalization Predictions in AI, Generating Neural Structures<\/td>\n<\/tr>\n \n 3. Recurrent and Lifelong Learning<\/td>\n \u00a0<\/td>\n<\/tr>\n \n March 2<\/td>\n Turing Capabilities and Super Turing Adaptivity<\/td>\n<\/tr>\n \n March 9<\/td>\n Time Series Prediction<\/td>\n<\/tr>\n \n March 16<\/td>\n Holiday – Spring Break<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n \n\n
\n March 23a<\/td>\n Lifelong Learning, Adaptive Architectures, Neuromodulations for Continual Adaptivity<\/td>\n<\/tr>\n \n 4. Memory in Biology and Engineering<\/td>\n \u00a0<\/td>\n<\/tr>\n \n March 23b<\/td>\n Stable Memories and Dynamical Systems, Hopfield Memories, Generalized Hopfield for Large Capacity<\/td>\n<\/tr>\n \n March 30<\/td>\n Dynamic Energy Landscape and Sequence-Memories, Lifelong Updates of Memories, and Biophysics<\/td>\n<\/tr>\n \n 5. Unlearning<\/td>\n \u00a0<\/td>\n<\/tr>\n \n April 6<\/td>\n Problem Learning and Hardship of Unlearning, Reconsolidation and Relaxing Fears<\/td>\n<\/tr>\n \n April 13a<\/td>\n Unlearning in AI and Data Science<\/td>\n<\/tr>\n \n April 13b<\/td>\n Projects: Concepts and Presentations<\/td>\n<\/tr>\n \n April 20<\/td>\n Holiday – Patriot’s Day<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n