Posts tagged deep-learning

Pooling Layers in Convolutional Neural Networks

How max and average pooling downsample a representation, the hyperparameters they take, and why they have no weights to learn.

• cnn
• computer-vision
• deep-learning
• Written in EN

Daniel Du
27 Feb 2023 · 2 min read

One Layer of a Convolutional Network

A step-by-step walk through a single convolutional layer: filters, bias, activation, and the parameter count it actually costs.

• cnn
• computer-vision
• deep-learning
• Written in EN

Daniel Du
27 Feb 2023 · 2 min read

Convolutions Over Volume

How convolution extends from flat images to 3D volumes, and why stacking multiple filters is what gives a CNN layer its depth.

• cnn
• computer-vision
• deep-learning
• Written in EN

Daniel Du
27 Feb 2023 · 3 min read

Deep Learning Computer Vision Advancements and Exciting Applications

How deep learning reshaped computer vision, from self-driving perception and face recognition to image recommendation and art generation.

• cnn
• computer-vision
• deep-learning
• Written in EN

Daniel Du
26 Feb 2023 · 3 min read

Deep Q-Learning (DQN)

Why tabular Q-learning breaks down in continuous state spaces, and how DQN replaces the Q-table with a neural network and a replay buffer.

• deep-learning
• reinforcement-learning
• Written in EN

Daniel Du
22 Feb 2023 · 1 min read

Understanding Padding in Convolutional Neural Networks

Why convolutions shrink a feature map, and how valid and same padding keep spatial resolution intact through a deep CNN.

• cnn
• computer-vision
• deep-learning
• Written in EN

Daniel Du
21 Feb 2022 · 3 min read