Multikernel activation functions: formulation and a case study
The design of activation functions is a growing research area in the field of neural networks. In particular, instead of using fixed point-wise functions (e.g., the rectified linear unit), several authors have proposed ways of learning these functions directly from the data in a non-parametric fashion. In this paper we focus on the kernel activation function (KAF), a recently proposed framework wherein each function is modeled as a one-dimensional kernel model, whose weights are adapted through standard backpropagation-based optimization. One drawback of KAFs is the need to select a single kernel function and its eventual hyper-parameters. To partially overcome this problem, we motivate an extension of the KAF model, in which multiple kernels are linearly combined at every neuron, inspired by the literature on multiple kernel learning. We provide an application of the resulting multi-KAF on a realistic use case, specifically handwritten Latin OCR, on a large dataset collected in the context of the `In Codice Ratio' project. Results show that multi-KAFs can improve the accuracy of the convolutional networks previously developed for the task, with faster convergence, even with a smaller number of overall parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
Optical Character Recognition (OCR)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neural Network Verification as Piecewise Linear Optimization: Formulations for the Composition of Staircase Functions
We present a technique for neural network verification using mixed-integer programming (MIP) formulations. We derive a \emph{strong formulation} for each neuron in a network using piecewise linear activation functions. A…
Multiplant Nonlinear System Identification by Block-Structured Multikernel Neural Networks in Applications of Interference Cancellation
Problems of linear system identification have closed-form solutions, e.g., using least-squares or maximum-likelihood methods on input-output data. However, already the seemingly simplest problems of nonlinear system iden…
Adaptive Learning in Cartesian Product of Reproducing Kernel Hilbert Spaces
We propose a novel adaptive learning algorithm based on iterative orthogonal projections in the Cartesian product of multiple reproducing kernel Hilbert spaces (RKHSs). The task is estimating/tracking nonlinear functions…
MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation
The automatic generation of deep learning (DL) kernels using large language models (LLMs) has emerged as a promising approach to reduce the manual effort and hardware-specific expertise required for writing high-performa…
Feed-Forward Neural Networks as a Mixed-Integer Program
Deep neural networks (DNNs) are widely studied in various applications. A DNN consists of layers of neurons that compute affine combinations, apply nonlinear operations, and produce corresponding activations. The rectifi…