Cheat sheet for exam
이 아이들을 A4 1장에 어떻게 잘 우겨 넣을 것인가.. 돋보기 챙겨가야 하는 거 아냐..? -_-
* Linear classifier: One template per class
* Neural net: first layer is bank of templates; Second layer recombines templates
- Can use different templates to cover multiple modes of a class!
- “Distributed representation”: Most templates not interpretable!
First-layer conv filters: local image templates (Often learns oriented edges, opposing colors)
For convolution with kernel size K, each element in the output depends on a K x K receptive field in the input
Each successive convolution adds K – 1 to the receptive field size. With L layers the receptive field size is 1 + L * (K – 1)
Input volume: 3 x 32 x 32
10 5x5 filters with stride 1, pad 2
Output volume size: 10 x 32 x 32
Number of learnable parameters: 760
Number of multiply-add operations: 768,000
10*32*32 = 10,240 outputs; each output is the inner product
of two 3x5x5 tensors (75 elems); total = 75*10240 = 768K
Most of the memory usage is in the early convolution layers
Nearly all parameters are in the fully-connected layers
Most floating-point ops occur in the convolution layers
