# The Modern Mathematics of Deep Learning

**URL:** <https://forum.devtalk.com/t/the-modern-mathematics-of-deep-learning/10521>\
**Category:** Data Science\
**Tags:** learning, pdf, mathematics, in-the-news\
**Created:** [14 June 2021 14:06 UTC](https://forum.devtalk.com/t/the-modern-mathematics-of-deep-learning/10521 "2021-06-14T14:06:23Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [14 June 2021 14:06 UTC](https://forum.devtalk.com/t/the-modern-mathematics-of-deep-learning/10521/1 "2021-06-14T14:06:23Z")

</div>

> The Modern Mathematics of Deep Learning.  
> We describe the new field of mathematical analysis of deep learning. This  
> field emerged around a list of research questions that were not answered within  
> the classical framework of learning theory. These questions concern: the  
> outstanding generalization power of overparametrized neural networks, the role  
> of depth in deep architectures, the apparent absence of the curse of  
> dimensionality, the surprisingly successful optimization performance despite  
> the non-convexity of the problem, understanding what features are learned, why  
> deep architectures perform exceptionally well in physical problems, and which  
> fine aspects of an architecture affect the behavior of a learning task in which  
> way. We present an overview of modern approaches that yield partial answers to  
> these questions. For selected approaches, we describe the main ideas in more  
> detail.

Read in full here:

> **[The Modern Mathematics of Deep Learning](https://arxiv.org/abs/2105.04026)**
>
> We describe the new field of mathematical analysis of deep learning. This field emerged around a list of research questions that were not answered within the classical framework of learning theory. These questions concern: the outstanding...

PDF here:

> **[2105.04026.pdf](https://arxiv.org/pdf/2105.04026.pdf)**
>
> 3.35 MB

_This thread was posted by one of our members via one of our news source trackers._