Implemented and applied kNN, Multiclass SVM classifiers with SVM and Softmax loss with techniques like Stochastic Gradient Descent and Cross-validation from scratch for the task of classifying Images from the CIFAR-10 dataset.
Developed Multi-layer Fully Connected Neural Networks with training techniques like Backpropagation, Batch Normalization and, Layer Normalization while using various optimization techniques (SGD, RMSProp, AdaGrad, Adam) for the task of Image Classification on CIFAR-10.
Implemented a VGG like CNN in PyTorch to achieve 80% for Image Classification on CIFAR-10.
Autonomous Navigation with Q-Learning
We guide an autonomous vehicle to its goal location by
designing and implementing a learning architecture using Q-Learning.
The Vehicle achieves this while avoiding any
static obstacles. We implemented Q-Learning
and Deep Q-Learning in order to navigate the Turtlebot3. We learned
numerous concepts of Reinforcement Learning, Q Learning,
Deep Q Learning and Model Predictive Control along the way.
designing and implementing a learning architecture using Q-Learning.
The Vehicle achieves this while avoiding any
static obstacles. We implemented Q-Learning
and Deep Q-Learning in order to navigate the Turtlebot3. We learned
numerous concepts of Reinforcement Learning, Q Learning,
Deep Q Learning and Model Predictive Control along the way.
