Deep Learning
6 milestones in AI history
Backpropagation Rediscovered
Rumelhart, Hinton, and Williams published 'Learning Representations by Back-propagating Errors' in Nature, demonstrating that backpropagation could train multi-layer neural networks effectively. The same year, the PDP (Parallel Distributed Processing) group published their influential two-volume work on connectionism.
LeNet: Convolutional Neural Networks
Yann LeCun demonstrated that convolutional neural networks (CNNs) could be trained with backpropagation to recognize handwritten digits. The refined LeNet-5 (1998) achieved 99%+ accuracy on MNIST and was deployed by banks to read checks — running in ATMs for years.
Deep Belief Networks: Hinton Revives Deep Learning
Geoffrey Hinton published 'A Fast Learning Algorithm for Deep Belief Nets,' showing that deep neural networks could be effectively trained by pre-training each layer as a restricted Boltzmann machine. This solved the long-standing problem of training networks with many layers.
AlexNet: The ImageNet Moment
AlexNet, a deep convolutional neural network, won the ImageNet competition by a staggering margin — reducing the error rate from 26% to 16%. Trained on two NVIDIA GTX 580 GPUs, it was dramatically deeper and more powerful than previous entries. The AI community was stunned.
DeepMind's DQN Masters Atari Games
DeepMind demonstrated a deep reinforcement learning agent (Deep Q-Network) that learned to play Atari 2600 games directly from pixel inputs, achieving superhuman performance on many games with no task-specific engineering. Google acquired DeepMind for ~$500 million shortly after.
ResNet: Deeper Than Ever
Microsoft Research introduced ResNet with skip connections (residual connections), enabling the training of networks with 152+ layers — 8x deeper than previous networks. ResNet won ImageNet 2015 with 3.57% error, surpassing human-level performance (5.1%) for the first time.