Geoffrey Hinton

AlexNet is a convolutional neural network (CNN) architecture that was developed by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton in 2012. …

Impressions on a new(?) learning procedure for neural networks — 2022 has gone away with Hinton’s last effort — The Forward-Forward Algorithm: Some Preliminary Investigations. It is not my intention to stir up a controversy about Hinton, but to this day it still escapes me what his real contribution to neural networks is. Last time I covered an article by…

Pix2Seq, Using Language Model for Object Detection, by Prof. Hinton, Outperforms Faster R-CNN and DETR — Pix2Seq: A Language Modeling Framework for Object Detection, Pix2Seq, by Google Research, Brain Team, 2022 ICLR, Over 50 Citations (Sik-Ho Tsang @ Medium) Object Detection, Language Model, LM, BERT, Transformer Unlike existing approaches that explicitly integrate prior knowledge about the task, Pix2Seq casts object detection as a language modeling task…

Yoshua Bengio, Geoffrey Hinton, and Yann LeCun Q&A — This time, I would like to share a Q&A interview of Yoshua Bengio, Geoffrey Hinton, and Yann LeCun, who are recipients of the 2018 ACM A.M. Turing Award. This is a magazine article from Communications of ACM (CACM) in 2019. (Sik-Ho Tsang @ Medium) 1. AI Inspired from the Brain

2018 Turing Award, 2021 Communications of the ACM — The Turing Award is often referred to as the computer science equivalent of the Nobel Prize. Yoshua Bengio, Yann LeCun, and Geoffrey Hinton are recipients of the 2018 ACM A.M. Turing Award for breakthroughs that have made deep neural networks a critical component of computing. This time, I would like…

MoE, By Hinton in 1991. Hinton Extended to NLP in 2017 — Adaptive Mixtures of Local Experts MoE, by MIT, and University of Toronto, 1991 JNEUCOM, Over 5000 Citations (Sik-Ho Tsang @ Medium) Mixture of Experts, MoE, Sequence Model, Vowel Recognition By using gating network, different experts are on/off based on the input signal. This is a paper by Prof. Hinton’s research…

Comparison Among Models From Last Story ResNet, Inception Net, and Exception Model focus on designing compact layers to address parameter redundancy and memory usage problem, while XNor-Net tries to reduce the parameter and speed up the network by defining a new method to do convolution. Moreover, ResNet aims to improve…

More often than not we’ve heard of sportsmen, politicians, and other inspiring figures all around the world and thought of being great like them in our times to come. That definitely is the case in this amazing industry where individuals have redefined the way we see Data Science by their…