Build CIFAR10 classifiers using Tensorflow, PyTorch, PyTorch Lightning

My project for two advanced training courses about machine learning and neural networks at educx (https://educx.de/).

Exploring machine learning with nueral networks for a charity analysis. Adjusting the model to try and improve accuracy to predict which projects are likely to be successful.

Deep learning models to detect cyber attacks based on the paper "Towards Developing Network forensic mechanism for Botnet Activities in the IoT based on Machine Learning Techniques"

Convolutional Neural Network on Images with and without Forest Fires

Examples of techniques that can be used to optimize neural network models (some techniques can apply more generally).

training, evaluation and api for forest-cover dataset

Using the features in the provided dataset, creating a binary classifier that can predict whether applicants will be successful if funded by Alphabet Soup.

Classifies wild cats images

Keras Tuner used for hyperparameter tuning the neural networks.

The notebook shows how deep learning tools (TensorFlow/Keras and PyTorch ) work in practice.

We used a dataset that included birth and personal data as well as Autism Spectrum Quotient test scores to train machine learning algorithms to predict autism. We used Logistic Regression, Neural Network Models and Keras Tuner with Random Oversampling to train one with 90% accuracy.

Neural Network experimentation on the CIFAR-10 dataset ( https://www.cs.toronto.edu/~kriz/cifar.html )

Deep learning projects, using TensorFlow Keras package

Utilized deep learning systems to classify brain MRI scans into glioma tumor, meningioma tumor, pituitary tumor, or no tumor. We addressed class imbalance using undersampling and augmented the dataset with rotation, shifting, shearing, zooming, and flipping techniques.

Histopathology Images Classification

Create a neural network through TensorFlow and Keras to build a model which has the ability to assess an organisation's ability to be successful with funding from the Alphabet Soup charity

A machine learning solution for automating nucleus detection in biomedical images, leveraging the U-Net architecture to accelerate medical research and disease treatment discovery.