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 operational workflows
- Verification of GPU availability, CUDA/cuDNN compatibility, and driver configurations for government applications
- Configuration of parallel workers, memory management, and foundational usage of
gpuArray - Lab 1: Environment validation and execution of the initial GPU-accelerated deep learning script
Core Deep Learning Constructs in MATLAB
- Neural network layer implementations: convolutional, pooling, batch normalization, dropout, residual, and dense layers
- Foundational concepts of
dlarray,dlnetwork, and custom training loop structures - Loss function definitions, optimizer selection (Adam, SGD, RMSProp), and learning rate scheduling strategies
- Visualization techniques for architectures, weight distributions, and gradient flow to facilitate debugging
- Lab 2: Construction of a custom
dlnetworkfrom scratch and analysis of layer interactions
Designing CNNs for Image Recognition
- Convolutional neural network design patterns: feature extraction, spatial hierarchies, and receptive field analysis
- Transfer learning methodologies utilizing pre-trained networks such as ResNet, EfficientNet, and MobileNet
- Implementation of data augmentation pipelines using
imageDatastore,augmentedImageDatastore, and custom transformations - Lab 3: Training a CNN from scratch on a custom image classification dataset with integrated augmentation
Automated Data Labeling & Reproducible Pipelines
- Utilization of MATLAB’s active learning and semi-supervised labeling capabilities for efficient data processing
- Standardized import and export of annotations (COCO, Pascal VOC, YOLO, CSV) for data interoperability
- Development of version-controlled, parameterized data preparation scripts to ensure auditability
- Lab 4: Automation of the labeling workflow and integration into a comprehensive training script
Scalable Training: Multi-GPU, Cloud & Clusters
- Multi-GPU training strategies: batch size optimization, gradient accumulation, and data parallelism techniques
- Distributed training implementation using MATLAB Parallel Server and on-premises cluster resources
- Cloud training workflows for government infrastructure (AWS, Azure, GCP) via MATLAB cloud compute profiles
- Training monitoring, checkpoint management, and hyperparameter optimization methods
- Lab 5: Scaling a model to a multi-GPU/cloud environment and profiling training throughput
Cross-Framework Interoperability & Model Exchange
- Importation of pre-trained Caffe and TensorFlow/Keras models into the MATLAB environment
- Verification of accuracy parity and architectural adaptation for MATLAB-based workflows
- Model export to ONNX, TensorFlow, or Core ML for cross-platform deployment and integration
- Lab 6: Importation of a TF-Keras model, fine-tuning within MATLAB, and export to ONNX format
Capstone Project & Production Readiness
- End-to-end pipeline execution: data ingestion, training, validation, optimization, and deployment
- Model compression techniques: pruning, quantization, and code generation utilizing GPU Coder
- Best practices for reproducibility: systematic logging, random seed management, and distribution of MATLAB deep learning applications
- Capstone: Development, training, optimization, and export of a complete image recognition system tailored to specific operational requirements
To request a customized course outline for this training for government, please contact us.
Requirements
- Demonstrated proficiency in MATLAB, including syntax, programming workflows, and toolbox familiarity
- No prior experience in data science or deep learning is required for entry into this course
- Access to a local GPU-enabled workstation (CUDA-compatible) or an approved cloud cluster for live laboratory exercises
Audience
- Developers & Software Engineers
- Research Engineers & Domain Experts
- Teams transitioning from traditional signal/image processing to AI-driven workflows for government operations
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
