nehamalcom / Deep-Learning-Projects

All the Deep Learning Projects I have been working on using Python.

Deep Learning Projects

1. Handwritten Digits Image Classification using Logistic Regression

I used the MNIST Handwritten Digits Database as our training dataset. Here I have used logistic regression and I am currently working on using a feed-forward neural network to better this existing model. Done for completing a course on Jovian.

2. Handwritten Digits Image Classification using Feed-Forward Neural Network

It is challenging to improve accuracy of a logistic regression model beyond 87%. We improve upon it using a feed-forward neural network which can capture non-linear relationships between inputs and targets. Done for completing a course on Jovian.

3. Insurance Cost Prediction using Linear Regression

I have used information like a person's age, sex, BMI, no. of children and smoking habit to predict the price of yearly medical bills. This kind of model is useful for insurance companies to determine the yearly insurance premium for a person. The dataset for this problem is taken from Kaggle. Done for completing a course on Jovian.

4. Everyday Object Image Classification using a Neural Network

We are using the CIFAR10 dataset: https://www.cs.toronto.edu/~kriz/cifar.html. We will set up a training pipeline to train a neural network on a GPU (if possible) and experiment with different network architectures & hyperparameters. Done for completing a course on Jovian.

4. Everyday Object Image Classification using a Convolutional Neural Network

We will better our previous project by using a 2D convolutional neural network with multiple layers. Done for completing a course on Jovian.