◑ Data science / Machine learning: Please refer "Machine learning specialized profile" for specific project details and know-how.
◐ Computational Linguistics / Computer vision : Please refer "Deep learning specialized profile" for specific project details and know-how.
Recent projects:
- Prototype development - Agriculture startup using computer vision
- Product development - Education tech startup: SOTA - State of the art highly engaging assistant with humanly conversations for researchers
- NLP: To detect hacking threats with NLP analysis for a gaming industry startup
- Data science POC : stock price prediction - (forecast and nowcast) using Echo state networks
- Custom Spacy NLP pipelines in bio medical and clinical domain
- Image classification - A. Textile patterns classification, B. Agriculture - plant disease detection
- Image segmentation - Healthcare
- ML/DL Decision support system (chatbot) - a healthcare startup
Approach:
- Applying ML/AI/DL for the implementation of new concepts and ideas from various fields.
- Assessing and providing the optimal solution using apt ML/DL libraries and tools for individual problem.
Services:
- EDA / ETL to grab pulse of the data
- Data pipeline strategizing,
- Data mining
- Statistical analysis
- Introduce Machine learning (ML), Deep learning (DL) in existing products / services,
- Data-driven Decision support systems,
- Scientific research projects,
- Start up product design / development (UI/UX web development/ mobile app),
Hands on:
Multi-class Classification, Regression, Neural Networks (CNN, RNN, bi-directional LSTM), Recommender Systems, Support Vector Machines (SVM), K-Means Clustering and Principal Component Analysis (PCA), Reinforcement Learning, Natural Language Processing (NLP), Computer vision( 2d/3D classification, detection, segmentation, pose estimation)
DL libraries:
TensorFlow, Keras, PyTorch, MACE, MXNet, fastAI, tflite
Databases:
MySQL, Postgres, MongoDB, Grakn, Neo4js
Data wrangling, text mining, data analysis and data visualization Tools:
Pandas, Dask, NumPy, Scikit-learn, MATLAB, Matplotlib, Seaborn, Plotly
Data pipelines - Active learning loops with:
Prodigy, Label Studio, Label box, AWS lambda functions
NLP Services:
Data scrapping, Parsing, Annotation, POS tagging, Stemming, Tokenization,
Named entity extraction, Text classification, Machine translation, Text summarization, Question and answers, Text generation, Sentiment analysis, Topic segmentation, Conversational chatbots
NLP Tools:
Word2vec, Doc2vec, NLTK, Gensim, Scispacy, SpaCy 3 with transformers, Dialogflow, RASA, Google BERT, Open AI GPT, Scispacy, Biograkn
Computer vision services:
Image Classification, Object Detection, Object counting, Image Segmentation, Human pose estimation
Computer vision Tools :
OpenCV, MobileNet, Efficientnet, Inception, DarkNet , Faster R-CNN, UNet, SegNet, Mask R-CNN, DeepLab, TensorFlow, Pytorch, MACE, MXNet, YOLO, COCO, SSD, Openpose, HR net, Posenet, Mediapipe, Detectron
Backend Tools:
Flask, Django, REST APIs
Product development / MVP or POC:
Web UIs, Flutter
Industry focus:
Mental health, Fintech, Climate, Agriculture