paper-with-me

홈 › Papers

Min-Max-Plus Neural Networks

2021-02-12 · Ye Luo, Shiqing Fan

We present a new model of neural networks called Min-Max-Plus Neural Networks (MMP-NNs) based on operations in tropical arithmetic. In general, an MMP-NN is composed of three types of alternately stacked layers, namely linear layers, min-plus layers and max-plus layers. Specifically, the latter two types of layers constitute the nonlinear part of the network which is trainable and more sophisticated compared to the nonlinear part of conventional neural networks. In addition, we show that with higher capability of nonlinearity expression, MMP-NNs are universal approximators of continuous functions, even when the number of multiplication operations is tremendously reduced (possibly to none in certain extreme cases). Furthermore, we formulate the backpropagation algorithm in the training process of MMP-NNs and introduce an algorithm of normalization to improve the rate of convergence in training.

📄 PDF Abstract BibTeX arXiv:2102.06358

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Squareplus: A Softplus-Like Algebraic Rectifier

2021-12-22 · Jonathan T. Barron

We present squareplus, an activation function that resembles softplus, but which can be computed using only algebraic operations: addition, multiplication, and square-root. Because squareplus is ~6x faster to evaluate th…

CPU

Surplus sharing with coherent utility functions

2018-10-28

We use the theory of coherent measures to look at the problem of surplus sharing in an insurance business. The surplus share of an insured is calculated by the surplus premium in the contract. The theory of coherent risk…

The Division of Surplus and the Burden of Proof

2025-01-24 · Deniz Kattwinkel, Justus Preusser

A surplus must be divided between a principal and an agent. Only the agent knows the surplus' true size and decides how much of it to reveal initially. Both parties can exert costly effort to conclusively prove the surpl…

AdaPlus: Integrating Nesterov Momentum and Precise Stepsize Adjustment on AdamW Basis

2023-09-05 · Lei Guan

This paper proposes an efficient optimizer called AdaPlus which integrates Nesterov momentum and precise stepsize adjustment on AdamW basis. AdaPlus combines the advantages of AdamW, Nadam, and AdaBelief and, in particul…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

Fitted Q-Iteration via Max-Plus-Linear Approximation

2024-09-12 · Y. Liu, M. A. S. Kolarijani

In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to p…