CLS Token in Vision Transformers
Trace how a learned CLS row joins image patches, gathers evidence through self-attention, and becomes the image-level classification readout.
Related
7 min read · beginner
ML Concepts - Page 2
Clear explanations of core machine learning concepts, from foundational ideas to advanced techniques. Understand attention mechanisms, transformers, skip connections, and more.
194
Total Concepts
341
Topics
Page 2
of 33
Concepts - Page 2
Browse by categoryASFF: Adaptive Spatial Feature Fusion
Learning where to fuse multi-scale features with per-pixel, per-level fusion weights. ASFF challenges FPN's uniform fusion assumption.
Related
15 min read · intermediate
Silhouette Score: Per-Point Clustering Evaluation
How the silhouette score measures clustering quality for every individual point — comparing intra-cluster cohesion to nearest-cluster separation, with per-point diagnostics that work for arbitrary cluster shapes.
Related
8 min read · intermediate
Sparse vs Dense vs Hybrid Retrieval: BM25, BERT, and Reranking Compared
How sparse retrieval (BM25/TF-IDF), dense retrieval (BERT-style embeddings), and hybrid systems that combine both compare on recall, semantic understanding, computational cost, and operational complexity for modern search.
Related
12 min read · beginner
Tensor Cores: Mixed Precision & Matrix Acceleration
How NVIDIA Tensor Cores accelerate GEMM: warp-level MMA, precision dials (TF32/FP16/BF16/INT8/FP8), shape alignment cliffs, AMP vs model.half(), and when the speedup actually shows up.
Related
16 min read · intermediate
PyTorch DataLoader Pipeline
PyTorch DataLoader deep dive — Dataset, Sampler, Workers, Collate internals, num_workers throughput profiling, memory analysis, serialization costs, production patterns (LMDB, WebDataset), and bottleneck diagnosis.
Related
22 min read · intermediate
Showing 7-12 of 194 concepts