paper-with-me

Papers

Training Very Deep Networks

2015-07-22 · NeurIPS 2015 12 · Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and training of very deep networks remains an open problem. Here we introduce a new architecture designed to overcome this. Our so-called highway networks allow unimpeded information flow across many layers on information highways. They are inspired by Long Short-Term Memory recurrent networks and use adaptive gating units to regulate the information flow. Even with hundreds of layers, highway networks can be trained directly through simple gradient descent. This enables the study of extremely deep and efficient architectures.

📄 PDF Abstract BibTeX arXiv:1507.06228

Code (3)

LiyuanLucasLiu/LM-LSTM-CRF pytorch
flukeskywalker/highway-networks
yoonkim/lstm-char-cnn torch

Tasks

Image Classification

Methods 이 논문이 사용한 방법론

Highway networks There is plenty of theoretical and empirical evidence that depth of neural networks is a crucial ingredient for their success. However, network training becomes more difficult…
Branch attention Branch attention can be seen as a dynamic branch selection mechanism: which to pay attention to, used with a multi-branch structure.

Similar Papers 제목 키워드 기반

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs

2025-09-03 · Haijun Zhang, Jinxiang Wang, Zhenhua Yu, Yanyong Zhang 외 arxiv

Large language models (LLMs) have made a profound impact across various fields due to their advanced capabilities. However, training these models at unprecedented scales requires extensive AI accelerator clusters and sop…

CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery

2020-11-05 · Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark C. Jeffrey 외

The paper proposes and optimizes a partial recovery training system, CPR, for recommendation models. CPR relaxes the consistency requirement by enabling non-failed nodes to proceed without loading checkpoints when a node…

EgoRecovery: Acquiring Failure Recovery Ability Through Human Recovery Demonstration

2026-07-22 · Zuhao Ge, Yuchen Zhou, Weitao Zhou, Minglei Li 외 arxiv

Robust embodied robots should be able to recover from failures and retry tasks in order to operate reliably in unstructured and noisy real-world environments. Achieving this capability requires training policies on data …

Does YOLO Really Need to See Every Training Image in Every Epoch?

2026-03-18 · Xingxing Xie, Jiahua Dong, Junwei Han, Gong Cheng arxiv

YOLO detectors are known for their fast inference speed, yet training them remains unexpectedly time-consuming due to their exhaustive pipeline that processes every training image in every epoch, even when many images ha…

CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery

2026-07-03 · Safia Fatima, Kai Olav Ellefsen, Leon Moonen arxiv

Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios. RL policies often stall in failure states, spending up to 70% of an…

Reinforcement Learning