Day97 Deep Learning Lecture Review - Lecture 15 (2)
Bias Mitigation Strategies: Loss Reweighting, Sampling & Synthetic Samples and Architectural Changes (OccamNets, Adversarial Training & DANN)
Recent posts
Day96 Deep Learning Lecture Review - Lecture 15 (1)
Model Comparison and Bias Mitigation; McNemar’s Test, Dataset Bias, and Bias Detection
Day95 Deep Learning Lecture Review - Lecture 14
AI Ethics; AI Safety, Key Issues, AGI (Artificial General Intelligence), and Current AI Models’ Challenges
Day94 Deep Learning Lecture Review - Lecture 13
Llama 3: Framework, Workflow (RMSNorm, Grouped Query Attention, RoPE, SwiGLU Attention), Pre-training & Post-training
Day93 Deep Learning Lecture Review - Fine-Tuning Models (2) & Prompt Engineering
Comparing Pre-trained model embeddings (ResNet+SBERT vs. CLIP) and Prompt Engineering (Short and Direct, Few-Shot Learning, & Expert Prompting)
Day92 Deep Learning Lecture Review - Fine-Tuning Models (1)
HW2: Understanding of LoRA and Pre-trained Model Embeddings (ResNet+SBERT) for Visual Question Answering (VQA)
Day91 Deep Learning Lecture Review - Optimizing Hyperparameters
Weights & Biases (W&B) for Monitoring and Fine-Tuning ResNet-18 and Post-Training Evaluations (Dying ReLU, Brightness Robustness)
Day90 Deep Learning Lecture Review - Background Knowledges
HW0: Softmax Properties, PyTorch Lightning, and DataLoader
Day89 ML Review - Ensemble Method (5)
Revisiting Ensemble Method, Random Forest, and XGBoost
Day88 Deep Learning Lecture Review - Lecture 10-12
Deep Learning & Numerical Precision(Floating Point), Hardware Considerations, and Distributed Model Training