"Simulations for the paper 'A Review Article On Gradient Descent Optimization Algorithms' by Sebastian Roeder"

Optimizing neural networks is crucial for achieving high performance in machine learning tasks. Optimization involves adjusting the weights and biases of the network to minimize the loss function. This process is essential for training deep learning models effectively and efficiently.

Siamese Neural Network used for signature verification with three different datasets

flexible and extensible implementation of a multithreaded feedforward neural network in Java including popular optimizers, wrapped up in a console user interface

AI-Face-Mask-Detector

From linear regression towards neural networks...

Comparison of the Momentum, RMSprop, and Adam optimization methods to GD and SGD for machine learning models using synthetic data to evaluate convergence speed and accuracy.

Machine Learning Course [ECE 501] - Spring 2023 - University of Tehran - Dr. A. Dehaqani, Dr. Tavassolipour

A research project on enhancing gradient optimization methods

This project aims to create a deep learning model for classifying fashion items using the Fashion MNIST dataset. Below, you can find the steps of the project and the results obtained.

Constructed time series analysis and recurrent neural networks in GDP prediction under the global pandemic. Grasped data from remote data access, added in employment rate, cases of infection and indices for better representation, evaluation and optimization.

Notes about LLaMA 2 model

Data Structures, Algorithms and Machine Learning Optimization

Implemented optimization algorithms, including Momentum, AdaGrad, RMSProp, and Adam, from scratch using only NumPy in Python. Implemented the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimizer and conducted a comparative analysis of its results with those obtained using Adam.

Beginner Machine Learning - submission task for beginner Machine Learning class

This is an implementation of different optimization algorithms such as: - Gradient Descent (stochastic - mini-batch - batch) - Momentum - NAG - Adagrad - RMS-prop - BFGS - Adam Also, most of them are implemented in vectorized form for multi-variate problems

Object recognition AI using deep learning

A collection of various gradient descent algorithms implemented in Python from scratch

This is the implementation of neural network with few hidden layers. These implementation is inspired by the course I took on Coursera with deeplearning.ai.