Tutorial on Hands-on Deep Learning for Industrial Applications



Abstract

Deep learning is a mature AI paradigm in both research and practice. Supported by a substantial evidence base, it demonstrates increasing potential for industrial electronics and industrial informatics applications in factory automation, energy, manufacturing, transport, communication and human interfaces. This tutorial aims to develop essential knowledge of deep learning with hands-on exercises in Python, using Google Collaboratory and Jupyter Notebooks. The tutorial will begin by exploring the structural elements of deep learning models, hyper-parameters, and comparison to standard machine learning algorithms, followed by the theory and application of deep neural networks(classification), convolutional neural networks (image processing), and recurrent neural networks (time-series prediction). Participants will conduct hands-on experiments of each technique using benchmark and real datasets, for training, testing and evaluation. Each technique will be demonstrated in the context of real-world projects in Industrial settings. The learning outcomes of this workshop are; the theoretical foundations of deep learning - when to use and in which settings, the design and development of deep learning models, rapid prototyping, evaluation and deployment using Python.

Requirements

Participants will access Google Collaboratory using a Gmail account. A laptop with an Internet browser and a stable Internet connection is mandatory.

Presenters

Prabod Rathnayaka, AI Research Lead
Centre for Data Analytics and Cognition, La Trobe University, Victoria, Australia
Tel: +61 3 9479 6468
e-mail: p.rathnayaka@latrobe.edu.au 

Prabod works in AI research and practical applications development. His areas of specialisation are image, video analysis capability with applications in energy, transport, and natural language understanding. His current work is on information fusion and modality independent learning for complex pattern recognition tasks across multiple modalities.  

Sachin Kahawala, Data Scientist
Dependable Communication and Computation Systems,Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Sweden
Tel: +46 (0)920 491578
e-mail: sachin.kahawala@ltu.se 

Sachin Kahawala is a Data Scientist at Lulea University Technology, working on energy efficient machine learning algorithms, FPGA and neuromorphic hardware implementations for practical, real-world problems and learning domains. His current work is on advancing unsupervised learning algorithms using vector symbolic architectures and sparse distributed representations for spiking neuron implementations.

Made in Webflow