# [AI knowledge learning]Convolution in One Dimension for Neural Networks

**After learning two-dimensional convolution, learning one-dimensional convolution will fall into a misunderstanding, mistakenly thinking that the one-dimensional convolution kernel is convolved on a line. However, in fact, the input of one-dimensional convolution is a vector and a convolution kernel, and the output is also a vector. In this course, you will learn the kernel, equation and backpropagation of one-dimensional convolution.**

**By Brandon Rohrer**

Senior computer scientist, author of Data Science and Robots English website. His articles cover all aspects of computer science and are perfect for the novice to learn, as well as for the experienced to reflect on research or career directions. As of now, his YouTube subscribers have reached 84,500.

__[Computer Science]1D convolution for neural networks, part 1: Sliding dot product__

__[Computer Science]1D convolution for neural networks, part 2: Convolution copies the kernel__

__[Computer Science]1D convolution for neural networks, part 3: Sliding dot product equations longhand__

__[Computer Science]1D convolution for neural networks, part 4: Convolution equation__

__[Computer Science]1D convolution for neural networks, part 5: Backpropagation__

__[Computer Science]1D convolution for neural networks, part 6: Input gradient__

__[Computer Science]1D convolution for neural networks, part 7: Weight gradient__

__[Computer Science]1D convolution for neural networks, part 8: Padding__

__[Computer Science]1D convolution for neural networks, part 9: Stride__

__[Computer Science]Implement 1D convolution, part 1: Convolution in Python from scratch__

__[Computer Science]Implement 1D convolution, part 2: Comparison with NumPy convolution()__

__[Computer Science]Implement 1D convolution, part 3: Create the convolution block__

__[Computer Science]Implement 1D convolution, part 4: Initialize the convolution block__

__[Computer Science]Implement 1D convolution, part 5: Forward and backward pass__

__[Computer Science]Implement 1D convolution, part 6: Multi-channel, multi-kernel convolutions__

__[Computer Science]Implement 1D convolution, part 7: Weight gradient and input gradient__

__[Computer Science]Build a 1D convolutional neural network, part 1: Create a test data set__

__[Computer Science]Build a 1D convolutional neural network , part 2: Collect the Cottonwood blocks__

__[Computer Science]Build a 1D convolutional neural network, part 4: Training, evaluation, reporting__

__[Computer Science]Build a 1D convolutional neural network, part 6: Text summary and loss history__

__[Computer Science]Build a 1D convolutional neural network, part 7: Evaluate the model__