krishnaamsk Goto Github PK

500-ai-machine-learning-deep-learning-computer-vision-nlp-projects-with-code

500 AI Machine learning Deep learning Computer vision NLP Projects with code

acoustic-deep-incremental-learning

ai

Repository of various AI models - LSTM, CNN, AutoEncoders, GAN and Reinforcement Learning

andrew-ng-notes

This is Andrew NG Coursera Handwritten Notes.

anomaly-detection-resources

Anomaly detection related books, papers, videos, and toolboxes

anomaly-detection-using-cgan-and-lstm-autoencoder

Fake Data + Real Data = CGAN

anomaly_tuning

Learning hyperparameters for unsupervised anomaly detection

applications-of-ai-for-anomaly-detection

Nvidia DLI workshop on AI-based anomaly detection techniques using GPU-accelerated XGBoost, deep learning-based autoencoders, and generative adversarial networks (GANs) and then implement and compare supervised and unsupervised learning techniques.

applied-machine-learning-explainability-techniques

Applied Machine Learning Explainability Techniques, published by Packt

attention-clx-stock-prediction

Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction

attention-forest

attention_based_pansharpening

Attention-Based Deep Learning model for performing fusion of Optical Remote Sensing Images (Low Resolution Multi-Spectral Image (LRMS) and Panchromatic image (PAN)) to generate a High Resolution Multi-Spectral Image (HRMS)

auto_lirpa

auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs

awesome-autodl

A curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.

awesome-automl

Curating a list of AutoML-related research, tools, projects and other resources

awesome-incremental-learning

Awesome Incremental Learning

bayesian-hyper-parameter-optimization-for-malware-detection-extended

Selected Paper from the AI-CyberSec 2021 Workshop in the 41st SGAI International Conference on Artificial Intelligence (MDPI Journal Electronics)

bert-tabnet-ensemble

Emsembling Text and Structured Nerual Network models

binary-image-classification-on-fashion-mnist-using-tensorflow-quantum-and-cirq

binary_classification_pennylane_keras

Classical-Quantum hybrid model for credit card fraud detection

building-a-cnn-network-using-keras-and-tensorflow-and-tune-hyperparameters

This code uses the income data set to predict whether a given data point has an income below or above $50k. This code also includes data visualization, Data preprocessing, and tuning various hyper parameters to see if the model performs better. The Code follows the following order: Loading the dataset Statistical information retrieved from the dataset Data visualizations Data Pre processing. (Normalization, One hot encoding, handling missing/corrupted values and outliers) Train test split Building a Neural Network. The tuning hyper parameters executed are as follows: Modelling it with different activation functions Changing the Drop out value Modelling the optimizer Adding early stopping Adding regularizations Defining a gradient clipping Performing K-fold cross validation

classification-on-fashion-mnist-with-tensorflow-tensorflow-quantum-and-cirq

classification-xgboost-bayesopt

A jupyter notebook for binary classification of breast cancer using XGBoost with Bayesian optimization.

credit-card-fraud-detection-using-autoencoders

we will use a neural network called an autoencoder to detect fraudulent credit/debit card transactions on a Kaggle dataset. We will introduce the importance of the business case, introduce autoencoders, perform an exploratory data analysis, and create and then evaluate the model. The model will be presented using Keras with a TensorFlow backend usi

crime-analysis

This Project is for Web Dev Internship NITT 2023

customxgboost

Modified XGBoost implementation from scratch with Numpy using Adam and RSMProp optimizers.

data-science-cheatsheet

A helpful 5-page machine learning cheatsheet to assist with exam reviews, interview prep, and anything in-between.

data_mining

Data Mining - EDA, Feature Selection, Standardize, Remove Global Outliers, Normalize, Feature Extraction (with PCA), Clustering, Classification (baseline models and hyperparameter tuning with GridSearchCV).

deep-learning-har

Convolutional and LSTM networks to classify human activity

deep-learning-notebooks

A series of Jupyter notebooks that walk you through NNs, CNNs, RNNs, LSTMs, GANs in python using Scikit-Learn and TensorFlow.