๐ŸŽ CS231N ยท ๆ–ฏๅฆ็ฆ๐Ÿ“ ่ทฏๅพ„ไบŒ ยท ่ง†่ง‰ๆ ธๅฟƒ

CS231N ยท Deep Learning for Computer Vision

ไธป่ฎฒ๏ผšFei-Fei Li ็ญ‰ ๏ฝœ Spring 2026 ๏ฝœ ๅฎ˜็ฝ‘๏ผšhttps://cs231n.stanford.edu
๐ŸŽฌ ่ฎฒไน‰+่ฎบๆ–‡ๅทฒๆœฌๅœฐๅŒ–๏ผ›่ง†้ข‘้œ€ๆ กๅ†…ๆƒ้™
๐Ÿ“‚ ๆๆ–™็›ฎๅฝ•๐ŸŒ ่ฏพ็จ‹ๅฎ˜็ฝ‘

ๆœฌๅœฐๆๆ–™

papers๏ผˆ14๏ผ‰

๐Ÿ“„ AlexNet_Imagenet_Classification.pdf๐Ÿ“„ Attention_is_All_You_Need.pdf๐Ÿ“„ DETR_End-to-End_Object_Detection.pdf๐Ÿ“„ DINO_Self-Supervised_ViTs.pdf๐Ÿ“„ FCN_Fully_Convolutional_Networks.pdf๐Ÿ“„ Fast_R-CNN.pdf๐Ÿ“„ Faster_R-CNN.pdf๐Ÿ“„ GoogLeNet_Going_Deeper_with_Convolutions.pdf๐Ÿ“„ R-CNN_Rich_feature_hierarchies.pdf๐Ÿ“„ ResNet_Deep_Residual_Learning.pdf๐Ÿ“„ VGGNet_Very_Deep_ConvNets.pdf๐Ÿ“„ ViT_An_Image_is_Worth_16x16_Words.pdf๐Ÿ“„ YOLO_You_Only_Look_Once.pdf๐Ÿ“„ lecun-98b_Efficient_Backprop.pdf

slides๏ผˆ22๏ผ‰

๐Ÿ“„ handout_derivatives.pdf๐Ÿ“„ handout_linear-backprop.pdf๐Ÿ“„ lecture_10.pdf๐Ÿ“„ lecture_11.pdf๐Ÿ“„ lecture_12.pdf๐Ÿ“„ lecture_13.pdf๐Ÿ“„ lecture_14.pdf๐Ÿ“„ lecture_15.pdf๐Ÿ“„ lecture_16.pdf๐Ÿ“„ lecture_1_part_1.pdf๐Ÿ“„ lecture_1_part_2.pdf๐Ÿ“„ lecture_2.pdf๐Ÿ“„ lecture_3.pdf๐Ÿ“„ lecture_4.pdf๐Ÿ“„ lecture_5.pdf๐Ÿ“„ lecture_6.pdf๐Ÿ“„ lecture_7.pdf๐Ÿ“„ lecture_8.pdf๐Ÿ“„ lecture_9.pdf๐Ÿ“„ section_2_backprop.pdf๐Ÿ“„ section_3_project.pdf๐Ÿ“„ section_5.pdf