This module teaches techniques for processing and analyzing text and image data, including building models for NLP and computer vision tasks like sentiment analysis, text classification, and image recognition.
Key Topics:
Natural Language Processing (NLP)
- Text Preprocessing: Tokenization, stop words, stemming, and lemmatization.
- Text Representation: Bag of Words, TF-IDF, Word2Vec, and GloVe embeddings.
- Language Models: Understanding BERT and GPT for tasks like text classification and sentiment analysis.
- Chatbots & Conversational AI: Designing chatbots using rule-based and machine learning methods.
Computer Vision (CV)
- Image Preprocessing: Image resizing, normalization, and data augmentation techniques.
- Feature Extraction: Edge detection, SIFT, and HOG features.
- Deep Learning for CV: Convolutional Neural Networks (CNNs), Transfer Learning, and Pretrained Models (e.g., VGG, ResNet, MobileNet).
- Object Detection: Techniques like YOLO, SSD, and Faster R-CNN.
- Image Classification & Segmentation: Semantic segmentation and instance segmentation using U-Net and Mask R-CNN.
Mini Projects:
Natural Language Processing (NLP)
- Sentiment Analysis on Social Media Data
- Text Summarizer
- Plagiarism Detection
Computer Vision (CV)
- Handwritten Digit Recognition
- Face Mask Detection
- Image Classification
- Object Detection in Real-Time
- Image Colorization
- Virtual Try-On System
