AlgoNet: C^∞ Smooth Algorithmic Neural Networks

05/16/2019
by   Felix Petersen, et al.
0

Artificial neural networks revolutionized many areas of computer science in recent years since they provide solutions to a number of previously unsolved problems. On the other hand, for many problems, classic algorithms exist, which typically exceed the accuracy and stability of neural networks. To combine these two concepts, we present a new kind of neural networks---algorithmic neural networks (AlgoNets). These networks integrate smooth versions of classic algorithms and data structures into the topology of neural networks. A forward AlgoNet includes algorithmic layers into existing architectures while a backward AlgoNet can solve inverse problems without or with only weak supervision. In addition, we present the algonet package, a PyTorch based library that includes, inter alia, a smooth evaluated programming language, a smooth 3D mesh renderer, and smooth sorting algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/27/2017

Neural network augmented inverse problems for PDEs

In this paper we show how to augment classical methods for inverse probl...
research
09/21/2023

Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems

Neural networks have become a prominent approach to solve inverse proble...
research
03/20/2023

Convergence Guarantees of Overparametrized Wide Deep Inverse Prior

Neural networks have become a prominent approach to solve inverse proble...
research
09/01/2022

Learning with Differentiable Algorithms

Classic algorithms and machine learning systems like neural networks are...
research
02/21/2022

On the Suitability of Neural Networks as Building Blocks for The Design of Efficient Learned Indexes

With the aim of obtaining time/space improvements in classic Data Struct...
research
12/17/2022

The Calderón's problem via DeepONets

We consider the Dirichlet-to-Neumann operator and the Calderón's mapping...
research
09/27/2018

Smooth Inter-layer Propagation of Stabilized Neural Networks for Classification

Recent work has studied the reasons for the remarkable performance of de...

Please sign up or login with your details

Forgot password? Click here to reset