https://www.youtube.com/watch?v=dJYGatp4SvA&list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r
understanding visual data
Learning
building artificial systems that learn from data and experience
Deep Learning
Hierarchical learning algorithms with many layers, very loosely inspired by the brain
artifical intelligence
how can you build a computer systems that can do things that people normally do
breif history of computer vision and deep learning
- hubel and wiesel, 1959
- larry roberts, 1963
- david marr, 1970s
perceptron
neocognitron - computational model and visual system, directly inspired by Hubel and Wiesel’s hierarchy of complex and simple cells
Interleaved simple cells(convolution) and complex cells (pooling)
→ no practical training algorithm
backprop : introduced backpropagation for computing gradients in neural networks, successfully trained perceptrons with multiple layers
convolutional network : applied backprop algorithm to a Neocognitron-like architecture
2012 - algorithms, data, computation resources
