Learning Logistic Circuits

02/27/2019
by   Yitao Liang, et al.
8

This paper proposes a new classification model called logistic circuits. On MNIST and Fashion datasets, our learning algorithm outperforms neural networks that have an order of magnitude more parameters. Yet, logistic circuits have a distinct origin in symbolic AI, forming a discriminative counterpart to probabilistic-logical circuits such as ACs, SPNs, and PSDDs. We show that parameter learning for logistic circuits is convex optimization, and that a simple local search algorithm can induce strong model structures from data.

READ FULL TEXT
02/07/2022

Tractable Boolean and Arithmetic Circuits

Tractable Boolean and arithmetic circuits have been studied extensively ...
10/05/2020

Symbolic Verification of Quantum Circuits

This short note proposes a symbolic approach for representing and reason...
05/11/2020

A Logical Characterization of Constant-Depth Circuits over the Reals

In this paper we give an Immerman's Theorem for real-valued computation....
10/07/2021

SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming

The goal of combining the robustness of neural networks and the expressi...
12/07/2015

Thinking Required

There exists a theory of a single general-purpose learning algorithm whi...
01/26/2021

Reverse Derivative Ascent: A Categorical Approach to Learning Boolean Circuits

We introduce Reverse Derivative Ascent: a categorical analogue of gradie...
09/09/2018

LDW-SCSA: Logistic Dynamic Weight based Sine Cosine Search Algorithm for Numerical Functions Optimization

Particle swarm optimization (PSO) and Sine Cosine algorithm (SCA) have b...