Building
Practical Solutions

Objective: To design, train and deploy a deep learning model capable of autonomously controlling a vehicle using computer vision techniques.

Tools: Python, Tensorflow, Keras, Convolutional Neural Networks (CNN), Machine Learning, Git, GitHub

Duties: Prepared and processed driving datasets, implemented CNN based on the NVIDIA self-driving car architecture, trained and validated the model and finally deployed the trained model for interference. Developed the scripts to load the trained model and generate real-time steering predictions in a simulated driving environment.

Result: Demonstrated applied machine learning techniques for autonomous systems. Gained hands on experience in data preprocessing, deep learning model, training and evaluation workflows and real time influence, enhancing understanding of AI- driven software solutions.

Objective: To design and implement a series of event-driven computing applications demonstrating deterministic and non-deterministic finite state automation, regular expressions and advanced event- handling concepts.

Tools: Java, Event- Driven Architecture, Finite State Automata, Regular Expression, Asynchronous Processing, Git, Github

Duties: Analyzed specifications, designed state-based architecture, implemented deterministic and non-deterministic automata simulators, developed event driven logic to process asynchronous inputs. Tested and refined solutions to ensure correctness, efficiency and compliance with the requirements.

Result: Developed a strong understanding of event-driven system design, state management, practical implementation of theoretical computer science concepts. Improved analytical and problem solving skills.