Total 163 · Clear filters
In October 2012 AlexNet, a deep neural network built by a University of Toronto team, won the ImageNet image-classification challenge by a wide margin. Its result showed that large neural networks trained on GPUs could outperform hand-designed vision methods.
A Kaggle competition run in August–October 2012 in which competitors predicted molecules' biological activities from numerical descriptors of their chemical structures; a deep-learning team led by Geoffrey Hinton took first place.
A Google Research team trained a 9-layer sparse autoencoder on 10 million unlabeled images, reported a face detector learned without face labels, and reached 15.8% accuracy on 20,000 ImageNet categories.
On October 10, 2011, Stanford Engineering opened three free online computer science courses — databases, machine learning and artificial intelligence — to anyone online. Enrolments ran from 66,000 to an unprecedented 160,000 students from over 190 countries, without Stanford credit.
In 2011 Microsoft Research reported that modelling thousands of senones with deep neural networks, trained on GPUs, sharply cut word errors compared with conventional Gaussian-mixture systems in large-vocabulary speech recognition.
A 2010 NIPS workshop on deep learning and unsupervised feature learning. Its cited papers examine pre-training and fine-tuning for speech recognition and connect earlier and later work in the field.
At ICDAR 2009, Alex Graves won three connected handwriting competitions — French, Farsi and Arabic — with LSTM networks trained using Connectionist Temporal Classification, the first time a recurrent neural network won an international contest.
CUDA is NVIDIA's software platform for running general-purpose programs on GPU cores. CUDA Toolkit 1.0 shipped in June 2007, turning graphics chips into parallel processors for science and later for deep learning.
Geoffrey Hinton dated the current popularity of "deep learning" to a 2006 paper on deep belief nets, but the same words had earlier uses, including Rina Dechter's work in 1986.
A 2004 CIFAR research program proposed by Geoffrey Hinton with Yoshua Bengio and David Fleet, which CIFAR describes as the starting point of the deep learning era and the predecessor of today's Learning in Machines & Brains program.
TD-Gammon was an IBM backgammon program built by Gerald Tesauro that taught itself to evaluate positions by playing against itself with temporal-difference learning, reaching a level just below top human players and becoming an early landmark for reinforcement learning.
The first NeurIPS conference was held in 1987 in Denver, with Ed Posner as conference president and Yaser Abu-Mostafa as program chairman; its proceedings were published as volume 0 of the series.
In October 1986 Rumelhart, Hinton and Williams published a Nature paper showing that networks with hidden units can learn useful internal representations by back-propagation — with the 1987 PDP volumes, a key publication of connectionism's second wave.
The Conference on Computer Vision and Pattern Recognition (CVPR) held its first meeting in Washington, DC in 1983, organised by Takeo Kanade and Dana H. Ballard. It became one of the central venues where computer vision research is presented and compared.
The first International Workshop on Machine Learning, held at Carnegie Mellon University in July 1980, was the meeting that grew into ICML, today one of the three main machine learning conferences.
In 1969 Marvin Minsky and Seymour Papert published Perceptrons, a mathematical analysis of what perceptrons cannot compute. The book is often credited with contributing to a decline in neural-network research.
