I'm a Machine Learning & AI Engineer with over 3 years of hands-on experience developing and deploying intelligent systems for real-world applications. My expertise spans Natural Language Processing (NLP), Computer Vision (CV), and Reinforcement Learning. I am passionate about leveraging cutting-edge technologies to solve complex challenges and drive innovation.\

🚀 My Skills

• Machine Learning Frameworks: TensorFlow, PyTorch, Scikit-learn, Keras, Hugging Face
• Natural Language Processing (NLP): Text classification, Named Entity Recognition, Transformer models (BERT, GPT), Text generation
• Computer Vision (CV): Object detection, Image classification, Image segmentation, OpenCV, YOLO, Faster-RCNN
• Reinforcement Learning: Q-Learning, Deep Q Networks (DQN), Proximal Policy Optimization (PPO)
• Backend Engineering: REST APIs, Microservices architecture, Cloud computing (AWS, GCP)
• Programming Languages: Python, Golang, JavaScript, Scala
• DevOps & Tools: Docker, Kubernetes, CI/CD pipelines
• Data Handling & Databases: SQL, NoSQL, Pandas, Numpy

🔥 What I'm working on

• Developing end-to-end AI systems that solve real-world problems in NLP, CV, and reinforcement learning.
• Building and optimizing backend systems to support scalable AI applications.
• Contributing to open-source projects related to AI and ML.
• Experimenting with AI ethics and ensuring fairness and transparency in machine learning models.

💡 What drives me

• Building innovative solutions that push the boundaries of AI and ML.
• Working on complex problems where AI can make a real impact on society.
• Continuously learning and improving my skills in both AI and software engineering.

📈 Projects

• Real-time Hand Gesture Recognition with 3D CNNs: PyTorch implementation of the Real-time Hand Gesture Detection and Classification Using Convolutional Neural Network and Resource Efficient 3D Convolutional Neural Network, codes and pretrained model.
• KAN-GPT: The PyTorch implementation of Generative Pre-Trained Transformer (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling.
• Music Genre Classification: This project aims to classify music genres. CNN architecture and the GTZAN dataset were used for model training. Finally, a Web Application was made with Flask.

🌱 Let's Connect

• LinkedIn: https://www.linkedin.com/in/dikshant-vashistha-bb632112a/
• Website: https://wwww.dikshantvashistha.com
• Email: [email protected]