paper-with-me

홈 › Papers

Progressive Learning for Systematic Design of Large Neural Networks

2017-10-23 · Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Partha P. Mitra, Mikael Skoglund

We develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The systematic design addresses the choice of network size and regularization of parameters. The number of nodes and layers in network increases in progression with the objective of consistently reducing an appropriate cost. Each layer is optimized at a time, where appropriate parameters are learned using convex optimization. Regularization parameters for convex optimization do not need a significant manual effort for tuning. We also use random instances for some weight matrices, and that helps to reduce the number of parameters we learn. The developed network is expected to show good generalization power due to appropriate regularization and use of random weights in the layers. This expectation is verified by extensive experiments for classification and regression problems, using standard databases.

📄 PDF Abstract BibTeX arXiv:1710.08177

Code (1)

viebboy/HeMLGOP 공식 구현

Similar Papers 제목 키워드 기반

Progressive Generation of Long Text with Pretrained Language Models

2020-06-28 · NAACL 2021 4 · Bowen Tan, Zichao Yang, Maruan AI-Shedivat, Eric P. Xing 외

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to…

Progressive Learned Image Compression for Machine Perception

2025-12-23 · Jungwoo Kim, Jun-Hyuk Kim, Jong-Seok Lee arxiv

Recent advances in learned image codecs have been extended from human perception toward machine perception. However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bits…

Image Compression

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

2025-12-10 · Tiwei Bie, Maosong Cao, Kun Chen, Lun Du 외 arxiv

This paper presents LLaDA2.0 -- a tuple of discrete diffusion large language models (dLLM) scaling up to 100B total parameters through systematic conversion from auto-regressive (AR) models -- establishing a new paradigm…

YODA: Teacher-Student Progressive Learning for Language Models

2024-01-28 · Jianqiao Lu, Wanjun Zhong, YuFei Wang, Zhijiang Guo 외

Although large language models (LLMs) have demonstrated adeptness in a range of tasks, they still lag behind human learning efficiency. This disparity is often linked to the inherent human capacity to learn from basic ex…

GSM8KMath

FineViT: Progressively Unlocking Fine-Grained Perception with Dense Recaptions

2026-03-18 · Peisen Zhao, Xiaopeng Zhang, Mingxing Xu, Ruoyu Sun 외 arxiv

While Multimodal Large Language Models (MLLMs) have experienced rapid advancements, their visual encoders frequently remain a performance bottleneck. Conventional CLIP-based encoders struggle with dense spatial tasks due…