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

Kreiman Lab News

Neuro 140/240: Biological and Artificial Intelligence

Harvard, Spring 2022

Class starts on Tuesday Jan 25th, 2022, 3-5pm

Northwest Building B108

Link to class website

This is a seminar-style course which provides a foundational overview of key ideas in Computational Neuroscience and the study of Biological Intelligence. At the same time, the course will connect the study of brains to the blossoming and rapid development of ideas in Artificial Intelligence. Topics covered include the biophysics of computation, neural networks, machine learning, bayesian models, theory of learning, deep convolutional networks, generative adversarial networks, neural coding, control and dynamics of neural activity, applications to brain-machine interfaces, connectomics, among others. Lectures will be taught by leading Harvard experts in the field.

Kreiman Lab News

At the interface of brain and machine

Beijing, Apr 20, 2021

Prof. Gabriel Kreiman’s lecture titled:

How brain computations can inspire new paths in AI

See also:

Bomatter P, Zhang M, Karev D, Madan S, Tseng C, Kreiman G (2021). When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes. International Conference on Computer Vision (ICCV) PDF

Casper S, Boix X, D’Amario V, Guo L, Schrimpf M, Vinken K, Kreiman G. (2021). Frivolous Units: Wider Networks are not really that Wide. AAAI Conference on Artificial Intelligence PDF

Kreiman G and Serre T (2020). Beyond the feedforward sweep: feedback computations in the visual cortex. Ann N Y Acad Sci. 1464:222-241. PDF

Jacquot V, Ying J, Kreiman G. (2020) Can Deep Learning Recognize Subtle Human Activities? Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 14244-14253. arXiv 2003.13852

Zhang M, Tseng C, Kreiman G. (2020) Putting visual object recognition in context. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 12982-12991. arXiv:1911.07349

Kreiman Lab News

Congratulations to Leonardo Pollina!

Leonardo Pollina
Leonardo Pollina, M. Sc.

Leonardo Pollina successfully defended his Master’s Thesis

His thesis is entitled: “Combining neurophysiology and computational modeling through VGG19”

Leonardo’s work was supported by the Bertarelli Foundation

Kreiman Lab News

Brains, Minds and Machines Summer Course 2021

Applications are now open for the 2021 edition of the Brain, Minds and Machines Summer Course in Woods Hole MA.

08/05/2021 – 08/26/2021

Link to application: