邏輯迴歸(logistic regression)之實作範例

Finding Donor for CharityML - Machine Learning Nanodegree from Udacity

A neural network (one input, three hidden, one output layer) to classify the MNIST handwritten digits

Basic level implementation of Neural Network

Predict a Pulsar Star using Stochastic Gradient Descent, K nearest neighbors, Support Vector Machine and Decision Tree classifiers.

Neural network-based character recognition using MATLAB. The algorithm does not rely on external ML modules, and is rigorously defined from scratch. A report is included which explains the theory, algorithm performance comparisons, and hyperparameter optimization.

Assignments of my CST Part II Deep Neural Networks unit

Project 2 Group C - Predicting FinTech Bootcamp Graduate Salaries

Fundamentals of Artificial Intelligence and Deep Learning Frameworks

Simple convolutional neural network (purely numpy) to classify the original MNIST dataset. My first project with a convnet. 🖼

Application and illustration of a wide range optimization methods

Gradient Descent is a technique used to fine-tune machine learning algorithms with differentiable loss functions. It's an open-ended mathematical expression, tirelessly calculating the first-order derivative of a loss function and making precise parameter adjustments.

A simplified explanation of gradient descent for linear regression in python using numpy

Implement of SVM using Stochastic gradient descent - Stony Brook CSE512 Machine learning

Compilation of different ML algorithms implemented from scratch (and optimized extensively) for the courses COL774: Machine Learning (Spring 2020) & COL772: Natural Language Processing (Fall 2020)

Utilizing deep learning to deblur images

This repository includes implementation of the basic optimization algorithms (Batch-Mini-stochatic)Gradient descents and NAG,Adagrad,RMSProp and Adam)

A project performing gradient descent and stochastic average gradient descent for matrix completion. The algorithms are tested on some synthetic data before being used on downscaled real X-ray absorption data from a spectromicroscopy experiment. The algorithms' behaviours and outputs are examined in the report.

Optimize Neural Network - Stochastic Gradient Descent algorithm.