Seminar for Theoretical Computer Science

On Monday, March 20, 2023, 15:00 hours, Davor Runje (airt, Zagreb) will hold lecture as part of Seminar for Theoretical Computer Science titled:

"Constrained Monotonic Neural Networks".

Lecture will be held in lecture room 104, Department of Mathematics.

All Seminar members, graduate students and others interested are invited.

Abstract: Deep neural networks are becoming increasingly popular in approximating arbitrary functions from noisy data. But wider adoption is being hindered by the need to explain such models and to impose additional constraints on them. Monotonicity constraint is one of the most requested properties in real-world scenarios and is the focus of this paper. One of the oldest ways to construct a monotonic fully connected neural network is to constrain its weights to be non-negative while employing a monotonic activation function. Unfortunately, this construction does not work with popular non-saturated activation functions such as ReLU, ELU, SELU etc, as it can only approximate convex functions. We show this shortcoming can be fixed by employing the original activation function for a part of the neurons in the layer and employing its point reflection for the other part. Our experiments show this approach of building monotonic deep neural networks has matching or better accuracy when compared to other state-of-the-art methods such as deep lattice networks or monotonic networks obtained by heuristic regularization. This method is the simplest one in the sense of having the least number of parameters and does not require any modifications to the learning procedure or steps post-learning steps.

Author: Božidar Tartaro
News list


University of Zagreb

University of Osijek

University of Split

  • Seminar for Topology
  • Seminar for Discrete Mathematics

University of Rijeka


Calendar of mathematical events 

Seminar reports (in Croatian)