Contrastive Learning
Master contrastive learning for vector embeddings: how InfoNCE loss and self-supervised techniques train models to create high-quality semantic representations.
Related
10 min read · advanced
ML Concepts - Page 6
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 6
of 33
Concepts - Page 6
Browse by categoryMulti-GPU Communication: NVLink, PCIe, and NCCL
How GPUs talk: the bandwidth cliff from HBM to Ethernet, NVLink 5 and GB200 NVL72 topologies, ring AllReduce step by step, and choosing between NCCL, Gloo, and MPI.
Related
14 min read · intermediate
Python Global Interpreter Lock (GIL)
Learn the CPython Global Interpreter Lock (GIL) from first principles: why it exists, how threads take turns, why I/O still works well, and when to use multiprocessing, asyncio, or native extensions.
Related
15 min read · intermediate
Filesystems: The Digital DNA of Data Storage
Explore Linux filesystems through interactive visuals. Learn VFS, compare ext4 vs Btrfs vs ZFS, and understand file operations.
Related
10 min read
Self-Attention in Vision Transformers
Follow one image patch through Q/K/V projection, scaled scores, row-wise softmax, value mixing, and the residual update inside a Vision Transformer.
Related
10 min read · beginner
DETR Explained: Object Detection with Transformers
Understanding end-to-end object detection with transformers, from DETR's object queries to bipartite matching and attention-based localization
Related
15 min read · advanced
Showing 31-36 of 194 concepts