Tag: #deep-learning
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 77 posts
[Deep RL] 10. Actor-Critic Methods: A2C and Hyperparameter Tuning
Understand the Actor-Critic architecture that solves the variance problem of REINFORCE, apply the A2C algorithm to Pong, and analyze the impact of key hyperparameters such as learning rate and entropy coefficient.
2026-03-19 · 8 min read #reinforcement-learning#deep-learning#ai#actor-critic[Deep RL] 07. DQN Extensions: Double DQN, Dueling DQN, Rainbow
Implement six core extension techniques that improve DQN performance (N-step, Double DQN, Noisy Networks, Prioritized Replay, Dueling DQN, Categorical DQN) and Rainbow which combines them all.
2026-03-19 · 11 min read #reinforcement-learning#deep-learning#ai#dqn[Deep RL] 04. Solving CartPole with the Cross-Entropy Method
Explore the taxonomy of reinforcement learning methods and solve CartPole and FrozenLake environments using the Cross-Entropy method.
2026-03-19 · 9 min read #reinforcement-learning#deep-learning#ai[Deep RL] 01. What is Reinforcement Learning: MDP and Fundamental Concepts
We compare three paradigms of machine learning, and explore the core components of reinforcement learning (agent, environment, reward) along with the mathematical foundations of Markov Decision Processes (MDP).
2026-03-19 · 9 min read #reinforcement-learning#deep-learning#aiNVIDIA GPU and CUDA Architecture Deep Dive: Why GPUs Dominate AI
From H100 hardware specs to Tensor Core WMMA API. A complete breakdown of the SIMT execution model, shared memory tiling, warp divergence, and why GPUs are purpose-built for AI workloads.
2026-03-18 · 14 min read #cuda#gpu#nvidia#matrix-multiplication#parallel-computingAMD GPU & ROCm Deep Dive: Can It Challenge CUDA for LLM Inference?
A thorough technical analysis of AMD MI300X with 192GB HBM3, the ROCm software stack, and HIP programming model. Includes real LLM serving benchmarks with vLLM and llama.cpp, and an honest assessment of strengths and wea
2026-03-18 · 14 min read #amd#rocm#gpu#mi300x#model-servingBuilding LLM from Scratch: Complete Guide to Understanding GPT through Code
A complete guide to building and understanding Large Language Models from scratch. Implement a full GPT architecture in PyTorch — from tokenizer to Transformer, pretraining, and fine-tuning.
2026-03-17 · 21 min read #llm#gpt#transformer#from-scratch#deep-learningCUDA Programming Complete Guide: GPU Parallel Computing Zero to Hero
A comprehensive guide to mastering CUDA programming from fundamentals to advanced optimization. Covers GPU architecture, kernel writing, memory optimization, mixed precision training, and cuDNN/cuBLAS usage with practica
2026-03-17 · 30 min read #cuda#gpu#gpu-cuda#parallel-computing#nvidiaTransformer Architecture Complete Analysis: From Attention to Modern LLMs
A complete guide to understanding Transformer architecture from scratch. Covers Self-Attention, Multi-Head Attention, Positional Encoding, and Encoder-Decoder structure through Flash Attention, RoPE, and GQA with formula
2026-03-17 · 22 min read #transformer#attention#deep-learning#nlp#aiTorch-Titan Complete Guide: Everything About Large-Scale Distributed Training with PyTorch
A complete guide to mastering large-scale LLM distributed training with PyTorch Titan (torchtitan). Covers FSDP2, pipeline parallelism, tensor parallelism, 4D parallelism, Flash Attention, and mixed precision with hands-
2026-03-17 · 19 min read #torch-titan#distributed-training#pytorch#fsdp#deep-learningTensorFlow & Keras Complete Guide: Zero to Hero - From Installation to Production Deployment
A comprehensive guide to mastering TensorFlow and Keras from basics to production deployment. Learn tensor operations, Keras APIs, CNN/RNN/Transformer, TensorBoard, TF-Serving, and TFLite with hands-on examples.
2026-03-17 · 26 min read #tensorflow#keras#deep-learning#ai#pythonDeep Learning Time Series Analysis Complete Guide: LSTM, Transformer, PatchTST, TimesFM
A comprehensive guide to mastering time series data with deep learning. From preprocessing and ARIMA to LSTM, Temporal Fusion Transformer, PatchTST, Mamba, and the latest foundation models like TimesFM — all with practic
2026-03-17 · 17 min read #time-series#lstm#transformer#forecasting#deep-learningSelf-Supervised Learning Complete Guide: SimCLR, MAE, DINO, CLIP
A comprehensive guide to mastering self-supervised learning. Learn how to train powerful representations without labels — from contrastive learning (SimCLR, MoCo) and masked autoencoders (MAE, BEiT) to DINO and CLIP — wi
2026-03-17 · 25 min read #self-supervised-learning#contrastive-learning#simclr#mae#dinoSpeech & Audio AI Complete Guide: ASR, TTS, Whisper, Wav2Vec to Voice Synthesis
A complete guide to speech and audio AI from fundamentals to cutting-edge techniques. Master audio signal processing, Mel Spectrogram, ASR (Whisper, Wav2Vec2), TTS (Tacotron, VITS), speaker diarization, and music generat
2026-03-17 · 16 min read #speech-recognition#tts#whisper#wav2vec#audio-processingDeep Learning Recommendation Systems Complete Guide: From Collaborative Filtering to LLM-based RecSys
A complete guide to recommendation systems from foundations to the latest deep learning techniques. Master collaborative filtering, Matrix Factorization, NCF, Two-Tower models, sequential recommendation, GNN-based approa
2026-03-17 · 18 min read #recommendation-system#collaborative-filtering#deep-learning#two-tower#llmPyTorch Advanced Techniques Complete Guide: torch.compile, Custom Ops, Memory Optimization
A complete guide to mastering PyTorch advanced techniques. Covers torch.compile, custom operators, memory optimization, Gradient Checkpointing, torch.vmap, functorch, and PyTorch Profiler with hands-on examples.
2026-03-17 · 17 min read #pytorch#advanced#torch-compile#memory-optimization#custom-operatorsNatural Language Processing Complete Guide: Zero to Hero - From Text Processing to LLMs
A comprehensive guide from NLP fundamentals to the latest LLMs. Learn text preprocessing, Word2Vec, RNN/LSTM, Attention, Transformer, BERT, and GPT step by step with practical code examples.
2026-03-17 · 33 min read #nlp#natural-language-processing#transformer#bert#gptMeta-Learning and Few-Shot Learning Complete Guide: MAML, Prototypical Networks, In-Context Learning
A complete guide to mastering meta-learning and few-shot learning. From "learning to learn" to MAML, Prototypical Networks, Matching Networks, Reptile, and In-Context Learning in LLMs — with hands-on code.
2026-03-17 · 24 min read #meta-learning#few-shot-learning#maml#prototypical-networks#in-context-learningMamba and State Space Models Complete Guide: Beyond Transformers
A complete guide to understanding Mamba and State Space Models (SSMs). We deeply analyze S4, H3, and Mamba 1/2 architectures that solve the quadratic complexity problem of Transformers, along with hybrid models like Mamb
2026-03-17 · 20 min read #mamba#state-space-model#ssm#deep-learning#sequence-modelingKnowledge Distillation Complete Guide: Model Compression and Lightweight Techniques
A complete guide to mastering knowledge distillation and model compression. Covers Teacher-Student learning, intermediate-layer distillation, relation-based distillation, structured pruning, weight sharing, and neural ar
2026-03-17 · 22 min read #knowledge-distillation#model-compression#pruning#deep-learning#ai