Results for "feedforward"
Transformer
Intermediate
Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.
Exploding Gradient
Intermediate
Gradients grow too large, causing divergence; mitigated by clipping, normalization, careful init.
Recurrent Neural Network
Intermediate
Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.
Universal Approximation Theorem
Intermediate
Neural networks can approximate any continuous function under certain conditions.
Open-Loop Control
Advanced
Control without feedback after execution begins.