Categories
Kreiman Lab News

Giorgia Dellaferrera gives a talk at ICML 2022

Dellaferrera at ICML
Giorgia Dellaferrera giving a talk at ICML

Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass. Dellaferrera and Kreiman, ICML 2022

Link to paper

Categories
Kreiman Lab News

Launch of the AI @ Harvard website

AI @ Harvard is an interdisciplinary enterprise, encompassing computer science, public health, medicine, law, public policy, business, the sciences, and more.

https://www.ai.harvard.edu/

Categories
Kreiman Lab News

PredNet: A deep neural network architecture for predictive coding

Bill Lotter explains the PredNet neural network architecture

See publication:
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

See also:

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

GitHub Page

Categories
Kreiman Lab News

What is the difference between human eyes and computer vision?

Story by Ben Dickson

https://thenextweb.com/news/whats-the-difference-between-human-eyes-and-computer-vision

Categories
Kreiman Lab News

Beauty is in the eye of the machine

Edmond de Belamy

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.