Skip to content
View NeuralImprint's full-sized avatar

Block or report NeuralImprint

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NeuralImprint/README.md

✿ Hi, I'm Ankit Thakur ✿

Research-driven AI Engineer • Machine Learning Enthusiast • Open Source Contributor

Building intelligent systems where research meets real-world impact.

I enjoy transforming ideas into practical AI solutions through curiosity, mathematics, and continuous learning.


✿ About Me

I'm a third-year B.Tech student in Information Technology Engineering specializing in Machine Learning and Data Analytics.

My interests span Artificial Intelligence, Machine Learning, Computer Vision, Natural Language Processing, Data Science, Multimodal AI, and Generative AI. I enjoy reading research papers, experimenting with new ideas, and building intelligent systems that solve meaningful real-world problems.

I believe the best technology comes from combining strong fundamentals with continuous curiosity, practical experimentation, and collaboration.


───── Research Interests ─────

- Artificial Intelligence - Machine Learning - Deep Learning - Computer Vision - Natural Language Processing - Multimodal AI - Image Processing - Remote Sensing - Data Science - Generative AI

───── Technical Stack ─────

Languages

PythonC++JavaSQLC

AI & Machine Learning

PyTorchTensorFlowScikit-LearnOpenCVHugging%20FaceFastAPILangChain

Data Science

NumPyPandasMatplotlibSeabornPlotlyPower BIExcelXGBoostStatistical%20ModelingLightGBMCatBoost

Data Engineering

Apache Spark ETL Data Wrangling Feature Engineering

Deployment & MLOps

Docker CUDA ONNX

LLM & AI

GeminiOpenAIVector%20EmbeddingsRAGPrompt%20EngineeringQdrant

Databases

MySQLMongoDBPostgreSQL

Developer Tools

GitGitHubLinuxVS%20CodeJupyterGoogle%20ColabKaggle


───── Featured Projects ─────

Reverse RAG Hallucination Firewall

Developed an evidence-based Reverse RAG framework for detecting and validating hallucinated LLM responses using semantic retrieval and citation verification.

Tech: Python • FastAPI • Gemini API • Qdrant • Vector Embeddings


Real-Time Audio Visual Deepfake Detection

Built a low-latency multimodal framework combining video, audio, and lip-sync analysis for real-time deepfake detection.

Tech: Python • PyTorch • OpenCV • EfficientNetV2-S • AASIST • SyncNet


AI Image Super Resolution

Developed a lightweight image enhancement framework using Knowledge Distillation and achieved high-quality reconstruction.

Tech: PyTorch • Restormer • Residual U-Net


Intelligent OCR Engine

Built an OCR pipeline for handwritten document understanding with keyword-based information retrieval and hybrid database indexing.

Tech: PaddleOCR • OpenCV • MongoDB • MySQL


Cloud Cluster Prediction

Developed a deep learning framework for cloud movement prediction using satellite imagery for weather forecasting.

Tech: TensorFlow • Keras • Remote Sensing


───── Experience ─────

CSIR – National Physical Laboratory

Research Intern

Working on visibility enhancement and image dehazing by improving Dark Channel Prior and Gray Channel methodologies through experimental research.


Defence Research & Development Organisation

Research Intern

Optimized handwritten OCR pipelines and developed intelligent document retrieval systems using hybrid databases.


Intel Unnati

AI Research Intern

Worked on image super-resolution using teacher-student knowledge distillation for lightweight image reconstruction.


Bharat Heavy Electricals Limited

Machine Learning Intern

Developed predictive maintenance models using industrial sensor data and built analytical dashboards for equipment monitoring.


Ganpat University

AI Research Intern

Designed a real-time AI-based intrusion detection and facial recognition system using open-set recognition.


Open Source

I actively contribute to open-source projects, enjoy collaborating with developers, and continuously explore new technologies through hands-on development and research.


Current Focus

  • Multimodal AI
  • Large Language Models
  • Computer Vision
  • AI Research
  • Open Source
  • Data Science
  • Intelligent Retrieval Systems

GitHub Statistics


───── 🌸 Let's Connect 🌸 ─────

LinkedIn

Email

LeetCode

Kaggle

Codeforces

Always open to collaborating on AI research, open-source projects, and innovative ideas.


Research. Learn. Build. Share.

Pinned Loading

  1. bps-rajora/Misinformation-detector bps-rajora/Misinformation-detector Public

    Jupyter Notebook 1

  2. HomeguardAI HomeguardAI Public

    Python 1

  3. Project-Abhaya Project-Abhaya Public

    Abhaya, an AI-assisted women’s healthcare platform to help women with smart menstrual tracking, early detection of PCOS, personal wellness, mental well-being, and expert consultation.

    Python 1

  4. Reverse-RAG-Suchi Reverse-RAG-Suchi Public

    Python

  5. vanshika114/grocery-management-system vanshika114/grocery-management-system Public

    A simple grocery management system to track items, inventory, and billing.

    JavaScript 5 5

  6. AgentWatch AgentWatch Public

    Forked from sreerevanth/AgentWatch

    AgentWatch — Real-time reasoning auditor and observability platform for AI agents. Catches silent failures in your agent's reasoning chain before they execute — not after they break production.

    Python