School of Artificial Intelligence & Generative AI · Advanced
Deep Learning & Computer Vision Engineering Course
Build deep-learning vision systems that can classify, detect, segment and understand visual content — then deploy them for real use.
Talk to an adviser on WhatsApp
Neural Network FoundationsDeep Learning Engineering WorkflowCNNs and Transfer LearningObject Detection and Segmentation
PyTorchTensorFlowNumPyMLflowW&B
How you will learn
What you will learn, module by module
Build practical deep-learning systems using neural networks and vision architectures. Progress from Neural Network Foundations to Computer Vision Engineering Capstone through guided labs, assessed projects, and portfolio evidence.
01Module 1 · 8 hoursNeural Network FoundationsImplement and train a small neural network, then visualise learning curves and failure modes.
Topics you will cover
- Perceptrons
- Activations
- Loss functions
- Backpropagation
- Gradient descent
- Regularisation
- Initialisation
- Optimisers
- Training loops
- Tools and platforms
- PyTorch or TensorFlow, NumPy
- Portfolio evidence
- Neural-network fundamentals notebook
- Assessment
- Notebook and quiz
02Module 2 · 8 hoursDeep Learning Engineering WorkflowBuild a reproducible image-classification training pipeline with checkpoints and metrics.
Topics you will cover
- Tensors
- Datasets/dataloaders
- GPU training
- Checkpoints
- Mixed precision
- Experiment tracking
- Reproducibility
- Debugging unstable training
- Tools and platforms
- PyTorch/TensorFlow, MLflow/W&B optional
- Portfolio evidence
- Reusable DL training template
- Assessment
- Training pipeline review
03Module 3 · 10 hoursCNNs and Transfer LearningFine-tune a pretrained model on a custom image dataset and compare frozen versus full fine-tuning.
Topics you will cover
- Convolutions
- Pooling
- Normalisation
- Augmentation
- Pretrained backbones
- Transfer learning
- Fine-tuning
- Class imbalance
- Tools and platforms
- PyTorch/TensorFlow, torchvision
- Portfolio evidence
- Transfer-learning image classifier
- Assessment
- Vision lab
04Module 4 · 10 hoursObject Detection and SegmentationTrain or adapt an object-detection/segmentation model for a real-world visual task.
Topics you will cover
- Detection concepts
- IoU
- Anchors
- Modern detectors
- Semantic/instance segmentation
- Evaluation with mAP/IoU
- Labeling strategy
- Tools and platforms
- Ultralytics/YOLO or equivalent, OpenCV
- Portfolio evidence
- Detection or segmentation demo
- Assessment
- Detection project
05Module 5 · 8 hoursVision Transformers and EmbeddingsCreate an image-similarity search or zero-shot classification prototype using embeddings.
Topics you will cover
- Attention intuition
- ViT
- Image embeddings
- Similarity search
- Zero-shot concepts
- Multimodal representation learning
- Tools and platforms
- Transformers, FAISS/vector DB optional
- Portfolio evidence
- Visual search prototype
- Assessment
- Embedding lab
06Module 6 · 8 hoursMultimodal AI and Vision-Language SystemsBuild a multimodal assistant that interprets product, document or inspection images.
Topics you will cover
- Image-to-text
- Visual question answering
- Multimodal prompting
- Document/image understanding
- Grounding
- Safety and evaluation
- Tools and platforms
- Multimodal model API/open models, Python
- Portfolio evidence
- Multimodal AI demo
- Assessment
- Prototype review
07Module 7 · 10 hoursOptimisation, Evaluation and Edge/Cloud DeploymentBenchmark model accuracy versus latency and deploy an inference endpoint.
Topics you will cover
- Quantisation
- Pruning awareness
- Batching
- Latency/throughput
- Model serving
- ONNX concepts
- Monitoring
- Drift in vision data
- Tools and platforms
- ONNX optional, FastAPI, Docker, Cloud endpoint
- Portfolio evidence
- Deployed vision endpoint
- Assessment
- Performance report
08Module 8 · 16 hoursComputer Vision Engineering CapstoneBuild an end-to-end vision system such as defect detection, document classification or retail visual search.
Topics you will cover
- Dataset strategy
- Annotation
- Training
- Evaluation
- Interpretability
- Deployment
- Documentation
- Product demo
- Tools and platforms
- PyTorch/TensorFlow, OpenCV, Docker, GitHub
- Portfolio evidence
- Production-style computer vision project
- Assessment
- Capstone rubric and presentation
Projects you will build
2 portfolio projects plus module evidence
Visual Defect Detection
Detect defects from product/industrial images and deploy inference.
Dataset strategy · Model · Evaluation · Inference API · DemoDocument/Image Intelligence
Classify and extract insight from document or product images using multimodal models.
Multimodal prototype · Evaluation set · Deployment notes Course value
Why this course
Computer vision work requires more than training a notebook model; learners must understand architectures, data pipelines, evaluation, deployment, and responsible use.
The curriculum progresses from Neural Network Foundations to Computer Vision Engineering Capstone, with guided labs, assessments, and two portfolio projects: Visual Defect Detection and Document/Image Intelligence.
Who this course is for
ML practitioners and developers moving into computer vision and deep learning engineering.
AdvancedAI & Generative AI Engineer
PrerequisitesLearners should understand Python and machine-learning fundamentals, including basic linear algebra and model evaluation.
What you will be able to do
- Implement and train a small neural network, then visualise learning curves and failure modes.
- Build a reproducible image-classification training pipeline with checkpoints and metrics.
- Fine-tune a pretrained model on a custom image dataset and compare frozen versus full fine-tuning.
- Train or adapt an object-detection/segmentation model for a real-world visual task.
- Create an image-similarity search or zero-shot classification prototype using embeddings.
- Benchmark model accuracy versus latency and deploy an inference endpoint.
- Build an end-to-end vision system such as defect detection, document classification or retail visual search.
Technology you will use in this course
PyTorchTensorFlowNumPyMLflowW&BtorchvisionUltralytics/YOLO or equivalentOpenCVTransformersFAISSVector DBMultimodal model APIOpen modelsPython
Career relevance
AI & Generative AI Engineer
This course supports the development of skills relevant to roles such as Computer Vision Engineer, Deep Learning Engineer, and AI Engineer. The strongest learner outcome is a portfolio that shows the problem, implementation, testing or evaluation, documentation and a clear explanation of decisions—not a certificate alone.
Course evidence and instruction
Discuss your learning pathway
Review prerequisites, learning format and project expectations with admissions before enrolment.
Get course guidanceExplore the course projects
Review the project briefs and deliverables to understand the work expected during the course.
Review project expectationsTechnology references
Technology names identify learning tools and do not imply an employer partnership or endorsement.
Microsoft
Clear answers before you enrol
Is the Deep Learning & Computer Vision course suitable for beginners?
This is an advanced-level course. Learners should understand Python and machine-learning fundamentals, including basic linear algebra and model evaluation.
What will I build during the course?
You will complete guided labs in every module and build two portfolio projects: Visual Defect Detection and Document/Image Intelligence. Deliverables include working files or code, documentation, testing or evaluation evidence, and a final presentation.
Which tools and platforms are covered?
Key tools include PyTorch, TensorFlow, NumPy, MLflow, W&B, torchvision, Ultralytics, and YOLO. Additional platforms are introduced in relevant modules through practical tasks, and the toolset may evolve as industry practice changes.
How long does the course take?
The course includes approximately 78 guided learning hours across 8 modules, normally delivered over 10–12 weeks depending on batch intensity and learner practice time.
Which career paths can this course support?
The curriculum supports the development of skills relevant to roles such as Computer Vision Engineer, Deep Learning Engineer, and AI Engineer. Career outcomes depend on prior experience, project quality, interview readiness and market conditions; employment is not guaranteed.
Will I receive mentor and career support?
The course includes live instruction, lab support, assignment feedback, project reviews and career preparation covering portfolio development, CV writing, LinkedIn profile improvement, and interview guidance.
Ready to start?
A-56, Sector-64, Noida, Uttar Pradesh – 201301Ready to start your Deep Learning & Computer Vision Engineering journey?
Review the full curriculum, experience a live class and confirm the right starting point before enrolling.