Fundamental Components of Deep Learning: A category-theoretic approach

计算机科学 人工智能 认识论 心理学 数理经济学 认知心理学 数学 哲学
作者
Bruno Gavranović
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:1
标识
DOI:10.48550/arxiv.2403.13001
摘要

Deep learning, despite its remarkable achievements, is still a young field. Like the early stages of many scientific disciplines, it is marked by the discovery of new phenomena, ad-hoc design decisions, and the lack of a uniform and compositional mathematical foundation. From the intricacies of the implementation of backpropagation, through a growing zoo of neural network architectures, to the new and poorly understood phenomena such as double descent, scaling laws or in-context learning, there are few unifying principles in deep learning. This thesis develops a novel mathematical foundation for deep learning based on the language of category theory. We develop a new framework that is a) end-to-end, b) unform, and c) not merely descriptive, but prescriptive, meaning it is amenable to direct implementation in programming languages with sufficient features. We also systematise many existing approaches, placing many existing constructions and concepts from the literature under the same umbrella. In Part I we identify and model two main properties of deep learning systems parametricity and bidirectionality by we expand on the previously defined construction of actegories and Para to study the former, and define weighted optics to study the latter. Combining them yields parametric weighted optics, a categorical model of artificial neural networks, and more. Part II justifies the abstractions from Part I, applying them to model backpropagation, architectures, and supervised learning. We provide a lens-theoretic axiomatisation of differentiation, covering not just smooth spaces, but discrete settings of boolean circuits as well. We survey existing, and develop new categorical models of neural network architectures. We formalise the notion of optimisers and lastly, combine all the existing concepts together, providing a uniform and compositional framework for supervised learning.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
YN发布了新的文献求助10
1秒前
李爱国的应助被蔡克东采纳,获得10
2秒前
完美芯发布了新的文献求助10
2秒前
可靠松思完成签到,获得积分10
3秒前
筱梦完成签到,获得积分10
4秒前
完美世界的应助被开心德地采纳,获得10
4秒前
4秒前
SSS完成签到,获得积分10
5秒前
幽默山槐完成签到,获得积分10
6秒前
Nole的应助被zheng采纳,获得10
6秒前
kunnao完成签到,获得积分10
7秒前
小马甲的应助被科研通管家采纳,获得10
8秒前
8秒前
无极微光的应助被科研通管家采纳,获得20
8秒前
嘿嘿发布了新的文献求助10
8秒前
Orange的应助被科研通管家采纳,获得10
8秒前
syvshc的应助被科研通管家采纳,获得10
8秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
8秒前
斯文败类的应助被科研通管家采纳,获得10
8秒前
Jun的应助被科研通管家采纳,获得10
9秒前
小蘑菇的应助被科研通管家采纳,获得10
9秒前
Hello的应助被科研通管家采纳,获得10
9秒前
Nole的应助被科研通管家采纳,获得10
9秒前
Matisse的应助被科研通管家采纳,获得10
9秒前
JamesPei的应助被科研通管家采纳,获得10
9秒前
molihuakai的应助被科研通管家采纳,获得10
9秒前
搜集达人的应助被科研通管家采纳,获得30
10秒前
hudirudi的应助被科研通管家采纳,获得50
10秒前
小蘑菇的应助被科研通管家采纳,获得10
10秒前
10秒前
Matisse的应助被科研通管家采纳,获得10
10秒前
充电宝的应助被科研通管家采纳,获得10
10秒前
10秒前
在水一方的应助被xixi采纳,获得10
10秒前
ztq完成签到 ,获得积分10
12秒前
Orange的应助被开心德地采纳,获得10
13秒前
慕雨倾欣发布了新的文献求助10
13秒前
YN发布了新的文献求助10
13秒前
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188563
求助须知:如何正确求助?哪些是违规求助? 9576328
关于积分的说明 21846521
捐赠科研通 7786563
什么是DOI,文献DOI怎么找? 3435354
关于科研通互助平台的介绍 2559627
邀请新用户注册赠送积分活动 2482336