Controlling the spectral norm of implicitly linear layers (e.g., convolutional layers)

Wavelet Scattering Transform applied for Geo Sciences.

Denoising Diffusion Medical Model (DDMM) on PyTorch for generating datasets of Acute Lymphoblastic Leukemia 🩺💜

This code trains a CNN in Keras to classify cell images (infected/uninfected). It sets up data generators, defines model architecture with convolutional layers, applies regularization, configures callbacks, and trains the model for binary classification.

Implementation of SoundtStream from the paper: "SoundStream: An End-to-End Neural Audio Codec"

CNN for Fashion Mnist

GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch

SANNet Neural Network Framework

Implementation of the NFNets from the paper: "ConvNets Match Vision Transformers at Scale" by Google Research

Code for Spectral Norm of Convolutional Layers with Circular and Zero Paddings and Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

Leveraging advanced image processing and deep learning, this project classifies plant images using a subset of the Plant Seedlings dataset. The dataset includes diverse plant species captured under varying conditions. This project holds significance within my Master's in Computer Vision at uOttawa (2023).

repository for archiving experiments with various families of "spatially" two-dimensional dynamical systems.

This library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated

A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.

A CNN is a kind of network architecture for deep learning algorithms and is specifically used for image recognition and tasks that involve the processing of pixel data. This repository contains the code for CNN with a categorical classification dataset.

In this project we have explored the use of imaging time series to enhance forecasting results with Neural Networks. The approach has revealed itself to be extremely promising as, both in combination with an LSTM architecture and without, it has out-performed the pure LSTM architecture by a solid margin within our test datasets.

Acceleration package for neural networks on multi-core CPUs

2D Convolution from NumPy

JavaFx Application for Convolutional Network to perfom Image Classification using Softmax Output Layer, Back Propagation, Gradient Descent, Partial Derivatives, Matrix Flattening, Matrix Unfolding, Concurrent Task, Performance Histogram, Confusion Matrix

Determine feasible grasp positions and orientations using a spherically transformed dataset.