39 citations · 52 across the 10 of their papers we have counts for
12 papers
An Exact Finite-dimensional Explicit Feature Map for Kernel Functions
Kamaledin Ghiasi-Shirazi, Mohammadreza Qaraei
Kernel methods in machine learning use a kernel function that takes two data points as input and returns their inner product after mapping them to a Hilbert space, implicitly and w…
Deep multi-prototype capsule networks
Saeid Abbassi, Kamaledin Ghiasi-Shirazi, Ahad Harati
Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform a…
On translating conditional statements into mathematical logic
Kamaledin Ghiasi-Shirazi
In this paper, we highlight a profound difference between conditional statements in mathematical logic and natural languages. This difference exists even when the conditional state…
PowerLinear Activation Functions with application to the first layer of CNNs
Kamyar Nasiri, Kamaledin Ghiasi-Shirazi
Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing. Since the convolution operato…
Neural Generalization of Multiple Kernel Learning
Ahmad Navid Ghanizadeh, Kamaledin Ghiasi-Shirazi, Reza Monsefi +1
Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these method…
Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks
Ramin Zarei Sabzevar, Kamaledin Ghiasi-Shirazi, Ahad Harati
Prototype-based learning (PbL) using a winner-take-all (WTA) network based on minimum Euclidean distance (ED-WTA) is an intuitive approach to multiclass classification. By construc…
Revisiting 2-3 Red-Black Trees with a Pedagogically Sound yet Efficient Deletion Algorithm: The Parity-Seeking Delete Algorithm
Kamaledin Ghiasi-Shirazi, Taraneh Ghandi, Ali Taghizadeh +1
Red-black (RB) trees are one of the most efficient variants of balanced binary search trees. However, they have always been blamed for being too complicated, hard to explain, and n…
Improving the Backpropagation Algorithm with Consequentialism Weight Updates over Mini-Batches
Naeem Paeedeh, Kamaledin Ghiasi-Shirazi
Many attempts took place to improve the adaptive filters that can also be useful to improve backpropagation (BP). Normalized least mean squares (NLMS) is one of the most successful…
Learning 2D Gabor Filters by Infinite Kernel Learning Regression
Kamaledin Ghiasi-Shirazi
Gabor functions have wide-spread applications in image processing and computer vision. In this paper, we prove that 2D Gabor functions are translation-invariant positive-definite k…
Generalizing the Convolution Operator in Convolutional Neural Networks
Kamaledin Ghiasi-Shirazi
Convolutional neural networks have become a main tool for solving many machine vision and machine learning problems. A major element of these networks is the convolution operator w…
A two-stage learning method for protein-protein interaction prediction
Amir Ahooye Atashin, Parsa Bagherzadeh, Kamaledin Ghiasi-Shirazi
In this paper, a new method for PPI (proteinprotein interaction) prediction is proposed. In PPI prediction, a reliable and sufficient number of training samples is not available, b…
Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification
Amir Ahooye Atashin, Kamaledin Ghiasi-Shirazi, Ahad Harati
Many machine learning problems such as speech recognition, gesture recognition, and handwriting recognition are concerned with simultaneous segmentation and labeling of sequence da…