Anika Shrivastava

GenAI Researcher | Deep Learning & Computer Vision Specialist
Mandi, IN.

About

Highly motivated GenAI Researcher with over 1 year of experience developing cutting-edge learning-based solutions for image processing and Natural Language Processing (NLP). Proficient in deep learning and computer vision, with a strong academic foundation in mathematics and high-dimensional data analysis. Proven ability to engineer and optimize complex AI models, achieving high accuracy and efficiency in real-world applications.

Work

YouVah Studio Pvt. Ltd.
|

ML Intern

→

Summary

Developed and optimized Natural Language Understanding (NLU) modules for chatbots, focusing on improving the accuracy of intent classification and real-time query interpretation.

Highlights

Engineered a BERT-based NLU module for chatbots, leveraging Hugging Face Transformers and scikit-learn to enhance named entity recognition and contextual intent analysis.

Enabled accurate interpretation of user queries in real-time conversations through advanced NLU model development.

Achieved an 83% intent classification accuracy on an internally curated test set by fine-tuning BERT and implementing robust input preprocessing techniques.

U.R. RAO Satellite Centre, ISRO
|

Internship

→

Summary

Designed and implemented automated pipelines for satellite telemetry data verification and anomaly detection, significantly reducing manual effort and improving data transmission reliability.

Highlights

Developed an automated pipeline for the verification of satellite telemetry (TM) PROM data and generation of structured test error reports.

Minimized manpower and manual error by 30% across 5 ground stations by implementing a supervised Machine Learning approach.

Implemented an anomaly detection pipeline leveraging the Random Forest algorithm, trained on labeled telemetry logs, to flag inconsistent or faulty data transmissions.

Achieved over 95% accuracy in detecting anomalies in satellite telemetry data, enhancing data integrity.

Education

IIT Mandi

→

M.Tech-Research

Communication and Signal Processing

Grade: 8.06 CGPA

Banasthali University

→

B. Tech

Electrical and Electronics Engineering

Grade: 8.13 CGPA

Publications

Latent Space Characterization of Autoencoder Variants

Published by

VISAPP, International Conference on Computer Vision Theory and Applications

Summary

Authored a research paper characterizing Convolutional Autoencoder (CAE) and Denoising Autoencoder (DAE) latent manifolds as stratified manifolds, and Variational Autoencoder (VAE) as smooth product manifolds of symmetric positive definite and semi-definite matrix manifolds. Selected for oral presentation at the International Conference on Computer Vision Theory and Applications in Porto, Portugal, with an acceptance rate of 43.8%. Collaborative work with Dr. Samar Agnihotri and Dr. Renu Rameshan from Vehant Technologies Pvt. Ltd.

Skills

Programming Languages

Python, C/C++, SQL.

Core Competencies

Computer Vision, Generative AI (GenAI), Large Language Models (LLM), Natural Language Processing (NLP), Retrieval-Augmented Generation (RAG), Model Fine-tuning, Prompt Optimization, API Integration, High-dimensional Data Analysis.

ML Frameworks & Libraries

TensorFlow, Keras, PyTorch, Pandas, NumPy, OpenCV, Scikit-learn, Matplotlib, Hugging Face.

Software & Tools

GitHub, VSCode, MLflow, AWS, LangChain, Ollama, Postman, Docker, Flask, Streamlit, FastAPI.

Projects

Blind Image Deconvolution using learning-based approach (Research objective)

→

Summary

Investigating latent spaces of autoencoders and developing a novel deep-learning solution for blind image deconvolution, aiming for robust reconstructions under diverse noise conditions.

Blind Spot Dilation Architecture for Image Denoising

→

Summary

Designed and trained a Multi-CNN Autoencoder model to reconstruct occluded regions and denoise images, achieving significant PSNR improvements without relying on clean-noisy image pairs.

Driver's Drowsiness Detection System

→

Summary

Developed a real-time drowsiness detection system utilizing CNNs and OpenCV for high-accuracy eye state classification and accident prevention.