ApexFlow
Senior Software Developer, Learning Andrej's Videos, Loving to share
Neural Network & GPT Lecture 1.22 Layer normalization, Dropout, and Summary
Neural Network & GPT Lecture 1.21 Multi-head Attention, FeedForward, and ResNet
Neural Network & GPT Lecture 1.20 Additional explanations of attention
Neural Network & GPT Lecture 1.19 Implement the attention block with query, key, and value
Neural Network & GPT Lecture 1.18 Use matrix multiplication to aggregate weights
Neural Network & GPT Lecture 1.17 Finish Bigram, Start self-attention
Neural Network & GPT Lecture 1.16 BigramLanguageModel, cross_entropy
Neural Network & GPT Lecture 1.15 Tokenizer, Block_size, and Batch_size
Neural Network & GPT Lecture 1.14 Build GPT
Neural Network & GPT babyGPT, finite state markov chain, Andrej's notebook
Neural Network & GPT Lecture 1.13 Finish Andrej's first video and following contents
Neural Network & GPT Lecture 1.12 Micrograd key summary
Neural Network & GPT Lecture 1.11 Binary Classification
Neural Network & GPT Lecture 1.10 MultiLayer Perceptron (MLP)
Neural Network & GPT Lecture 1.5 Forward pass coding
Neural Network & GPT Lecture 1.9 Tensor, Neuron, and Layer
Neural Network & GPT Lecture 1.8 Can we split tanh() function?
Neural Network & GPT Lecture 1.7 A bug in gradient and __radd__
Neural Network & GPT Lecture 1.6 Backward propagation coding
Neural Network & GPT Lecture 1.4 Backward propagation
Neural Network & GPT Lecture 1.3 Forward pass
Neural Network & GPT Lecture 1.2 Basic Python coding
Neural Network & GPT Lecture 1.1 A starter
GPU零开销线程切换:揭秘Warp高效调度奥秘
GPU架构与CUDA执行模型?看懂这一篇就够了
AI如何“看懂”词义?Embedding与RAG的语言奥秘揭秘
大语言模型养成记, 从书呆子到职场精英
你的手机每秒能算10亿次?聊聊FLOPS这个算力"大高个"
CPU与GPU:米其林主厨与食堂大妈的计算奇妙比喻
显卡与GPU揭秘:发动机与整车的奥秘解析