Master contrastive learning for vector embeddings: how InfoNCE loss and self-supervised techniques train models to create high-quality semantic representations.

Contrastive Learning

Understand contrastive loss for representation learning: interactive demos of InfoNCE, triplet loss, and embedding space clustering with temperature tuning.

Contrastive Loss

The modality gap in CLIP and vision-language models: why image and text embeddings occupy separate regions despite contrastive training.

The Modality Gap

Learning low-dimensional vector representations of graphs through random walks, DeepWalk, Node2Vec, and skip-gram models

Interactive visualization of graph embedding techniques including DeepWalk, Node2Vec, random walk strategies, and skip-gram training

representation-learning

Concepts Related to representation-learning

Contrastive Learning

Contrastive Loss

The Modality Gap

Graph Embeddings