Devlog video about how I compute gradients in LeNet.
In my opinion, the gradients of max pooling and convolution can be tricky.
Welcome to the channel! I'm exploring AI and machine learning technologies, sharing insights, updates, and behind-the-scenes looks at my development process. If you’re into AI, machine learning, or tech innovation, this is the place for you.
0:00 Intro
1:04 Computing Gradients
1:22 Fix `lenet_convolution()` for Inputs with Shape 4
5:11 Future Optimization Plans
5:30 Realizing `convolution()` and `max_pool()` Can Be Moved to `lyr` Files
7:50 Moving Parameters Inside `lenet_train()`
8:24 Explaining Why `s4` Needs Reshaping
10:18 Computing Gradients for `dl/dc3`
13:20 Outro
#machinelearning #deeplearning #forwardpropagation #backpropagation #devlog
