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.
Course Outline
MATLAB Deep Learning Environment & GPU Validation
- Overview of Deep Learning Toolbox architecture and workflows
- Verifying GPU availability, CUDA/cuDNN compatibility, and driver configuration
- Configuring parallel workers, managing memory, and mastering
gpuArrayfundamentals - Lab 1: Validating the environment and executing your first GPU-accelerated deep learning script
Core Deep Learning Constructs in MATLAB
- Neural network layers: conv, pooling, batch normalization, dropout, residual, and dense layers
- Essentials of
dlarray,dlnetwork, and custom training loops - Loss functions, optimizers (Adam, SGD, RMSProp), and learning rate scheduling strategies
- Visualizing architectures, weight distributions, and gradient flow for effective debugging
- Lab 2: Constructing a custom
dlnetworkfrom scratch and debugging 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 with
imageDatastore,augmentedImageDatastore, and custom transforms - Lab 3: Training a CNN from scratch on a custom image classification dataset using augmentation
Automated Data Labeling & Reproducible Pipelines
- Utilizing MATLAB’s active learning and semi-supervised labeling tools
- Importing and exporting annotations (COCO, Pascal VOC, YOLO, 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: batch size tuning, gradient accumulation, and data parallelism
- Distributed training using MATLAB Parallel Server and on-premises clusters
- Cloud training workflows (AWS, Azure, GCP) via MATLAB cloud compute profiles
- Monitoring training, implementing checkpointing, and optimizing hyperparameters
- Lab 5: Scaling a model to a multi-GPU or cloud setup and profiling training throughput
Cross-Framework Interoperability & Model Exchange
- Importing pre-trained Caffe and TensorFlow/Keras models into MATLAB
- Validating accuracy parity and adapting architectures for MATLAB workflows
- Exporting models to ONNX, TensorFlow, or Core ML for cross-platform deployment
- Lab 6: Importing a TF-Keras model, fine-tuning it in MATLAB, and exporting to ONNX
Capstone Project & Production Readiness
- End-to-end pipeline: data ingestion, training, validation, optimization, and deployment
- Model compression: pruning, quantization, and code generation with GPU Coder
- Reproducibility best practices: logging, seeding, and sharing MATLAB deep learning apps
- Capstone: Building, training, optimizing, and exporting a complete image recognition system tailored to your specific domain
To request a customized course outline for this training, please contact us.
Requirements
- Proficiency in MATLAB, including syntax, programming workflows, and toolbox familiarity
- No prior experience in data science or deep learning is required
- Access to a local GPU-enabled workstation (CUDA-compatible) or an approved cloud cluster for live labs
Audience
- Developers and Software Engineers
- Research Engineers and Domain Experts
- Teams transitioning from traditional signal and image processing to AI-driven workflows
14 Hours
Testimonials (2)
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
Magdalena - Samsung Electronics Polska Sp. z o.o.
Course - Deep Learning with TensorFlow 2
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
