Machine learning algorithms in Dart programming language

The Pytorch Implementation of L-Softmax

My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition

Recognize one of six human activities such as standing, sitting, and walking using a Softmax Classifier trained on mobile phone sensor data.

Read and process CIFAR10 dataset, implement SVM and Softmax classifiers, train , and also tune up hyper parameters.

Plots how the logit values that are passed into the softmax function change over time as the model is trained.

Code for the Paper : NBC-Softmax : Darkweb Author fingerprinting and migration tracking (https://arxiv.org/abs/2212.08184)

Neural Network to predict which wearable is shown from the Fashion MNIST dataset using a single hidden layer

A data classification using MLP

Deep Learning breast histology microscopy image recognition using Convolutional Neural Networks

Developed a Convolutional Neural Network based on VGG16 architecture to diagnose COVID-19 and classify chest X-rays of patients suffering from COVID-19, Ground Glass Opacity and Viral Pneumonia. This repository contains the link to the dataset, python code for visualizing the obtained data and developing the model using Keras API.

Classifying fruit types using a deep learning method, namely Convolutional Neural Network (CNN/ConvNet), which is a type of artificial neural network that is generally used in image recognition and processing. And carry out the process of improvement mode with transfer learning.

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.

斯坦福大学cs231n课程的第一项作业之我的解答。Solution for Assignment1 (Images classification, kNN, SVM, SoftMax, FullyConnected Neural Network)

Image classifier which classifies MNIST database of handwritten digits 0-9 using 28x28 pixel images

🦠| Sentiment analysis on tweets about covid-19 vaccinations using Soft-max Regression, FNN, RNN and BERT-Base-uncased.

Repository contains neural network for classification using softmax as an activation function

Applied Softmax Classifier on Cifar10 Dataset

Classifying the following 5 types of flowers: Rose, Daisy, Dandelion, Sunflower and Tulip

Compared 3 Machine learning algorithms namely Softmax classification, K nearest neighbours and Multilayer Perceptron using F-1 scoring on Breast Cancer Wisconsin dataset. Used Features based on digitized image of a fine needle aspirate (FNA) of a breast mass. Used Scikit SKLearn to Implement the 3 models.