paper-with-me

홈 › Papers

Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond

2021-09-06 · Moacir Antonelli Ponti, Fernando Pereira dos Santos, Leo Sampaio Ferraz Ribeiro, Gabriel Biscaro Cavallari

Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be particularly useful in datasets that are not as well-prepared as those in challenges, and also under scarce annotation and/or small data. We describe basic procedures: as data preparation, optimization and transfer learning, but also recent architectural choices such as use of transformer modules, alternative convolutional layers, activation functions, wide and deep networks, as well as training procedures including as curriculum, contrastive and self-supervised learning.

📄 PDF Abstract BibTeX arXiv:2109.02752

Code (1)

maponti/trainingdeepnetworks 공식 구현

Tasks

Self-Supervised LearningTransfer Learning

Similar Papers 제목 키워드 기반

From Zero to Hero: Convincing with Extremely Complicated Math

2023-04-01 · Maximilian Weiherer, Bernhard Egger

Becoming a (super) hero is almost every kid's dream. During their sheltered childhood, they do whatever it takes to grow up to be one. Work hard, play hard -- all day long. But as they're getting older, distractions are …

Math

Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning

2026-01-14 · Zhoubin Kou, Zihan Chen, Jing Yang, Cong Shen arxiv

Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a central issue in SFL and can be mitigated with auxiliary netw…

Federated Learning

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

2026-04-02 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg arxiv

We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionar…

Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

2022-05-16 · NAACL (WNU) 2022 7 · Dominik Stammbach, Maria Antoniak, Elliott Ash

This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, …

ArticlesQuestion Answering

ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers

2023-10-26 · Zhewei Yao, Reza Yazdani Aminabadi, Stephen Youn, Xiaoxia Wu 외

Quantization techniques are pivotal in reducing the memory and computational demands of deep neural network inference. Existing solutions, such as ZeroQuant, offer dynamic quantization for models like BERT and GPT but ov…

Quantization