Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
MATLAB Deep Learning Environment & GPU Validation
- Overview of the Deep Learning Toolbox architecture and workflow
- Checking for GPU availability, verifying CUDA/cuDNN compatibility, and configuring drivers
- Setting up parallel workers, managing memory, and getting started with the basics of
gpuArray - Lab 1: Validating the environment and executing your first GPU-accelerated deep learning script
Core Deep Learning Constructs in MATLAB
- Neural network layers: convolutional, pooling, batch normalization, dropout, residual, and dense layers
- Foundations of
dlarray,dlnetwork, and creating custom training loops - Loss functions, optimizers (Adam, SGD, RMSProp), and strategies for learning rate scheduling
- Visualizing network architectures, weight distributions, and gradient flow for effective debugging
- Lab 2: Creating a custom
dlnetworkfrom the ground up and troubleshooting layer interactions
Designing CNNs for Image Recognition
- CNN design patterns: feature extraction, spatial hierarchies, and receptive fields
- Transfer learning: utilizing pre-trained networks such as ResNet, EfficientNet, and MobileNet
- Creating data augmentation pipelines using
imageDatastore,augmentedImageDatastore, and custom transformations - Lab 3: Training a CNN from scratch on a custom image classification dataset using augmentation techniques
Automated Data Labeling & Reproducible Pipelines
- Utilizing MATLAB’s active learning and semi-supervised labeling tools
- Importing and exporting annotations in formats such as COCO, Pascal VOC, YOLO, and CSV
- Developing version-controlled, parameterized data preparation scripts
- Lab 4: Automating the labeling workflow and integrating it into the training script
Scalable Training: Multi-GPU, Cloud & Clusters
- Multi-GPU training strategies: adjusting batch sizes, gradient accumulation, and data parallelism
- Distributed training using MATLAB Parallel Server and on-premises clusters
- Cloud training workflows (AWS, Azure, GCP) utilizing MATLAB cloud compute profiles
- Monitoring training progress, checkpointing, and hyperparameter optimization techniques
- Lab 5: Scaling a model to a multi-GPU/cloud environment and profiling training throughput
Cross-Framework Interoperability & Model Exchange
- Importing pre-trained Caffe and TensorFlow/Keras models into MATLAB
- Verifying accuracy consistency and adapting architectures to fit MATLAB workflows
- Exporting models to ONNX, TensorFlow, or Core ML for cross-platform deployment
- Lab 6: Importing a TF-Keras model, fine-tuning it within MATLAB, and exporting it to ONNX
Capstone Project & Production Readiness
- End-to-end pipeline: data ingestion, training, validation, optimization, and deployment
- Model compression techniques: pruning, quantization, and code generation using GPU Coder
- Best practices for reproducibility: logging, seeding, and sharing MATLAB deep learning apps
- Capstone: Build, train, optimize, and export a complete image recognition system tailored to your specific domain
For a customized course outline tailored to this training, please get in touch with us.
Requirements
- Solid proficiency in MATLAB, including syntax, programming workflows, and familiarity with toolboxes
- No prior experience in data science or deep learning is necessary
- Access to a local GPU-enabled workstation (compatible with CUDA) or an approved cloud cluster for practical labs
Audience
- Developers & Software Engineers
- Research Engineers & Domain Experts
- Teams shifting from traditional signal or image processing to AI-driven workflows
Testimonials (2)
Getting people that never used AI some repetition in prompting and people that do use AI to consider different methods to using it.
Matthew Gay - Tarsus Pharmaceuticals
Course - Artificial Intelligence (AI) Overview
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at
