Building Neural Networks
Yann reflects on the early days of neural network development, sharing how he and Leon implemented a neural net simulator before the advent of popular frameworks like TensorFlow and PyTorch. He details the challenges of creating convolutional nets and the significance of shared weights in their architecture. By the end of 1988, his work at Bell Labs led to groundbreaking results on a sizable dataset, showcasing the potential of deep learning long before it became mainstream.In this clip
From this podcast
The Gradient
Yann LeCun on his Start in Research and Self-Supervised Learning
Related Questions