Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass. Dellaferrera and Kreiman, ICML 2022
AI @ Harvard is an interdisciplinary enterprise, encompassing computer science, public health, medicine, law, public policy, business, the sciences, and more.
Bill Lotter explains the PredNet neural network architecture
Lotter W, Kreiman G, Cox D. (2020) A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception. Nature Machine Intelligence, 2:210-219 PDF
Tang H, Schrimpf M, Lotter W, Moerman C, Paredes A, Ortega Caro J, Hardesty W, Cox D, Kreiman G. (2018) Recurrent computations for visual pattern completion. PNAS, 115:8835-8840. PDF
Lotter W, Kreiman, G, Cox, D. (2017) Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning. International Conference on Learning Representations (ICLR), Toulon, France. PDF
Lotter, W, Kreiman, G, Cox, D. (2016.) Unsupervised representation learning using predictive generative works. International Conference on Learning Representations (ICLR), Puerto Rico. PDF
Perspective article by Mengmi Zhang. Nature Human Behavior (2021).
Ansel Adams said, “There are no rules for good photographs, there are only good photographs.” Is it possible to predict our fickle and subjective appraisal of ‘aesthetically pleasing’ visual art? Iigaya et al. used an artificial intelligence approach to show how human aesthetic preference can be partially explained as an integration of hierarchical constituent image features.