Train neural networks for image tasks and implement a guided computer-vision pipeline from model evaluation to demonstration deployment. 1. Who can join
Suitable for: Python learners, AI students and image-processing enthusiasts Mandatory prerequisites: Python basics, NumPy and introductory machine-learning ideas; algebra helpful 2. Duration
52 live hours • Approximately 9 weeks at 6 hours per week; actual timetable to be confirmed. 3. Mode
Classroom - Thaiyur / Kelambakkam, OMR Chennai (subject to schedule)
Live Online (subject to schedule) 4. Syllabus — five modules
Module 1: Neural Network Math: Forward/Backpropagation & Loss Functions in PyTorch Learning outcome: Train a simple neural network and explain gradients and loss. Module 2: Convolutional Neural Networks (CNNs) & Image Feature Extraction Learning outcome: Build a CNN classifier and interpret image feature maps. Module 3: Real-Time Object Detection & Tracking with YOLOv8/v9 Learning outcome: Run and assess object detection and tracking on video samples. Module 4: Image Segmentation & Generative Vision Models Learning outcome: Explore segmentation and compare representative vision models. Module 5: Model Quantization & Deployment to Edge Devices (ONNX, TensorRT) Learning outcome: Export a model for inference and benchmark its performance on a chosen device. 5. Practical project
Source capstone title: Deploy a Real-Time Edge Video Analytics System for Security Monitoring Student deliverable: A prototype video analytics application that detects chosen objects in recorded or camera footage, displays results and documents its limitations.
6. What is included Live trainer-led sessions Practical assignments Sample code or templates, as applicable Project feedback Learning assessment Perizona course-completion certificate subject to assessment 7. Upcoming batch Start date: To be announced. Students can register interest; dates are shared only after confirmation.
