Completed
Implement 1D convolution, part 7: Weight gradient and input gradient
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Convolution in One Dimension for Neural Networks
Automatically move to the next video in the Classroom when playback concludes
- 1 1D convolution for neural networks, part 1: Sliding dot product
- 2 1D convolution for neural networks, part 2: Convolution copies the kernel
- 3 1D convolution for neural networks, part 3: Sliding dot product equations longhand
- 4 1D convolution for neural networks, part 4: Convolution equation
- 5 1D convolution for neural networks, part 5: Backpropagation
- 6 1D convolution for neural networks, part 6: Input gradient
- 7 1D convolution for neural networks, part 7: Weight gradient
- 8 1D convolution for neural networks, part 8: Padding
- 9 1D convolution for neural networks, part 9: Stride
- 10 Implement 1D convolution, part 1: Convolution in Python from scratch
- 11 Implement 1D convolution, part 2: Comparison with NumPy convolution()
- 12 Implement 1D convolution, part 3: Create the convolution block
- 13 Implement 1D convolution, part 4: Initialize the convolution block
- 14 Implement 1D convolution, part 5: Forward and backward pass
- 15 Implement 1D convolution, part 6: Multi-channel, multi-kernel convolutions
- 16 Implement 1D convolution, part 7: Weight gradient and input gradient
- 17 Build a 1D convolutional neural network, part 1: Create a test data set
- 18 Build a 1D convolutional neural network , part 2: Collect the Cottonwood blocks
- 19 Build a 1D convolutional neural network , part 3: Connect the blocks into a network structure
- 20 Build a 1D convolutional neural network, part 4: Training, evaluation, reporting
- 21 Build a 1D convolutional neural network, part 5: One Hot, Flatten, and Logging blocks
- 22 Build a 1D convolutional neural network, part 6: Text summary and loss history
- 23 Build a 1D convolutional neural network, part 7: Evaluate the model
