Skip to content
All tags

#cnn

4 posts
tech Reading Harvard CS50 AI

Harvard CS50 AI Week 5: Neural Networks — Backpropagation, TensorFlow/Keras, CNN & Traffic Sign Classification

Week 5 enters deep learning: perceptron to multi-layer nets, backprop chain rule, loss functions, optimizers, TensorFlow/Keras modeling, CNN conv/pool. Project Traffic trains CNN to classify traffic signs.

#harvard-cs50ai#ai#neural-networks#backpropagation#tensorflow#keras#cnn#traffic#python#cs50
tech deep-dive MIT 6.7960 Fall 2024 OCW Guide

MIT 6.7960 L05: CNN Architectures — From Convolution Kernels to Translation Equivariance

Lec 4 core: why CNN is the natural choice for grid data — convolution, translation equivariance, pooling, and classic architectures in one go

#mit-67960#deep-learning#pytorch#cnn#convolution#translation-equivariance#pooling
tech MIT 6.7960 導讀 (Fall 2024 OCW)

MIT 6.7960 L06: Modern CNN Architectures — ResNet, EfficientNet, ConvNeXt

ResNet's skip connections solve degradation, enabling 100+ layer nets; EfficientNet compound scales depth/width/resolution; ConvNeXt absorbs Transformer design to reclaim CV crown.

#mit-67960#deep-learning#cnn#resnet#pytorch#fall-2024
ai deep-dive Reading CMU 07-280

CMU 07-280 Lecture 14: Encoding Image Structure with Convolutional Networks

Lecture 14 replaces dense image models with local connectivity and parameter sharing, moving from convolution, stride, padding, and pooling to AlexNet, GPU data parallelism, ResNet skip connections, and BatchNorm.

#cmu#ai-course#computer-vision#cnn#alexnet