zchen0420 / nn_papers

To record my paper reading in my native language, mimicking ooooohira-san.
0 stars 0 forks source link

miscellaneous #7

Open zchen0420 opened 2 months ago

zchen0420 commented 2 months ago

What We Know About The Voynich Manuscript

zchen0420 commented 2 months ago

First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models

zchen0420 commented 2 months ago

Case-Based Reasoning for Natural Language Queries over Knowledge Bases

EMNLP 2021

借助已有的知识去解决复杂的问题:case-based reasoning (CBR) CBR-KBQA:a nonparametric memory存储cases (问题和logical forms) + a parametric model

zchen0420 commented 2 months ago

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

数学拟合/状态机

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

U-Mamba: Enhancing Long-range Dependency For Biomedical Image Segmentation

像U-Net

KAN: Kolmogorov–Arnold Networks

2024.4 | MIT, CIT, NEU, and NSF Institute | 视频 结偶复杂函数(多元近似单元合成:精确解、解析解;小波变换,样条插值)

对比feature:

zchen0420 commented 2 months ago

Distilling the Knowledge in a Neural Network

2015 | Geoffrey Hinton, Oriol Vinyals, and Jeff Dean | Google

Distillation: 🐛→🪲(原因:幼虫为成虫提供了很强适应性)🧑‍🏫→🧑‍🎓(老师不仅教课本的知识,还有自己的内化和感受。学生不是直接接触第一手的01世界,而是老师处理过的、包含更多信息的soft target。)

18年当时我老想着改softmax,但是Hinton却利用现有softmax形成两层的知识结构。巧妙。

【再度一遍看看公式和实验细节】

zchen0420 commented 1 month ago

Digital Humanities

2023

[2022]()

zchen0420 commented 1 month ago

semantic change / embedding space

Enriching Word Usage Graphs with Cluster Definitions

选取200个Word Usage(句子),标注他们之间的远近程度并训练模型泛化这个距离。

Norm of Word Embedding Encodes Information Gain

概率和条件概率之间的差: $KL(w) := KL(p(\cdot|w)||p(\cdot))$ LIME for BERT

A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection

zchen0420 commented 1 month ago

Zhuoyuan Mao