Computer vision and multimodal learning · MLD-0201
Connectionist temporal classification
A sequence-training objective that sums over valid alignments between longer inputs and shorter label sequences.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Train speech recognition without frame-level transcripts.
Original caveat
Standard CTC makes conditional-independence assumptions about output positions.
Context and aliases
Level: Intermediate. Stages: Architecture · Training · Inference.
Tags: DL · Audio · Multimodal.
Aliases: CTC.
Related concepts
Concepts linking here
Original references
- Learning Transferable Visual Models From Natural Language Supervision ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗