arXiv:1509.08101
Representation Benefits of Deep Feedforward Networks
원문 초록
This note provides a family of classification problems, indexed by a positive integer $k$, where all shallow networks with fewer than exponentially (in $k$) many nodes exhibit error at least $1/6$, whereas a deep network with 2 nodes in each of $2k$ layers achieves zero error, as does a recurrent network with 3 distinct nodes iterated $k$ times. The proof is elementary, and the networks are standard feedforward networks with ReLU (Rectified Linear Unit) nonlinearities.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database
Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions
ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation
Calibrating Translation Decoding with Quality Estimation on LLMs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.