Neural networks on digit recognition. As part of the MITx course on machine learning with Python - from linear models to deep learning
-
Updated
Aug 10, 2024 - Python
Neural networks on digit recognition. As part of the MITx course on machine learning with Python - from linear models to deep learning
Developed a CNN model to classify skin moles as benign or malignant using a balanced dataset from Kaggle, achieving a test accuracy of 81.82% and an AUC of 89.06%. Implemented data preprocessing by resizing images to 224x224 pixels and normalizing pixel values, enhancing model performance and stability.
This project demonstrates a complete pipeline for recognizing handwritten digits using the MNIST dataset. The project is implemented in Python using Jupyter Notebook, and it covers data loading, preprocessing, model training, and performance evaluation of a Fully Connected Neural Network (FCNN).
A collection of Deep Learning labs for the INSAT Data Science course.
Implementations of components of Neural Networks from scratch in Numpy
Building fully connected neural network from zero without using deep learning libraries such as Pytorch.
Enjoy the major Deep Learning Projects !!!
An implementation of the iris flower classification using Keras on the iris dataset
Fully Convolutional Neural Network for heart segmentation
A ROS1 self-driving car for the "Autonomous Driving Competition". The vehicle itself is a DonkeyCar with RaspberryPi and Raspberry Pi Camera.
Ford Otosan Internship Project 2020 || Freespace Segmentation.
Detection of Diabetic Retinopathy using a Fully Connected Neural Network for Data Processing (Tensorflow 1.12.0 and Python 3.6.6)
Classification of 3 species of flowers (versicolor, virginica, setosa) belonging to the Iris family, using a Fully Connected Neural Network for Data Processing (Tensorflow 1.12.0 and Python 3.6.6)
Concise neural network with C++ and CUDA
This project is about training a deep neural network to identify and track a target in simulation using Udacity's RoboND drone simulator. 🛸 Applications like this are key to many fields of robotics and the techniques applied can be extended to scenarios like advanced cruise control in autonomous vehicles or human-robot collaboration. 👨🏫
Predicting the closing stock price given last N days' data that also includes the output feature for CNN & LSTM, while predicting it for regular NN given only today's data, observing and comparing time series for various models. Additionally finding best value for N previous days and bidirectional LSTM for experiments.
Add a description, image, and links to the fcnn topic page so that developers can more easily learn about it.
To associate your repository with the fcnn topic, visit your repo's landing page and select "manage topics."