sgd-optimizer

PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"

Lookahead optimizer ("Lookahead Optimizer: k steps forward, 1 step back") for tensorflow

Implementation of (overlap) local SGD in Pytorch

A compressed adaptive optimizer for training large-scale deep learning models using PyTorch

Implement some ML algorithms in scala

Code for IoT Journal paper title 'ML-MCU: A Framework to Train ML Classifiers on MCU-based IoT Edge Devices'

Implement a Neural Network trained with back propagation in Python

Communication-efficient decentralized SGD (Pytorch)

Simple MATLAB toolbox for deep learning network: Version 1.0.3

Computer Vision and Image Processing algorithms implemented using OpenCV, NumPy and MatPlotLib, for UOM's EN2550 Fundamentals of Image Processing and Machine Vision Module ❄

ND-Adam is a tailored version of Adam for training DNNs.

A Repository to Visualize the training of Linear Model by optimizers such as SGD, Adam, RMSProp, AdamW, ASMGrad etc

Tensorflow-Keras callback implementing arXiv 1712.07628

This was a project case study on nonlinear optimization. We implemented the Stochastic Quasi-Newton method, the Stochastic Proximal Gradient method and applied both to a dictionary learning problem.

Implemented fully-connected DNN of arbitrary depth with Batch Norm and Dropout, three-layer ConvNet with Spatial Batch Norm in NumPy. The update rules used for training are SGD, SGD+Momentum, RMSProp and Adam. Implemented three block ResNet in PyTorch, with 10 epochs of training achieves 73.60% accuracy on test set.

基于粒子群PSO+随机梯度下降SGD优化器的Pytorch训练框架

An image classification app using the CIFAR10 dataset and CNNs. Containerised in Docker.

A simple classifier of music genders, Naive bayes, SGD and SVM used.

Activity recognition aims to recognize the actions and goals of one or more agents from a series of observations on the agents' actions and the environmental conditions.

In this repository, I have used CNN to MNIST Digit Classification Dataset. You can get insights about Convolutional Neural Network and its implementation for Handwritten Digit Classification.

LeNet5 on MNIST with SGD and Adam

The Deep Learning exercises provided in DataCamp

Notebooks with various models for images recognition based on dices example

A simple AI and machine-learning library written in python.

Deep Learning Optimizers

Design and train a network that combines supervised and unsupervised architecture in one model to achieve a classification task

Part of CMSC498L coursework. In this project, we implement binary classification of Images and Movie Reviews by implementing standard strategies of a two-layer fully-connected nerual network. SGD is used as an optimizer. The project contains the python notebook, which will give an in-depth walk-through through the steps adopted to train the model.

Demo dataset credits to NCTU 2020 autumn Machine Learning.

Using Keras to build a deep neural network for bladder cancer progression

Image Recognition using Python on MNIST dataset with the help of CNN, Multiclass Logistic Regression and SGD