Demystifying deep learning

A practical approach in MATLAB

Talk

By: Paola Jaramillo
From: The Mathworks

Talk at Meetup 20180419

Abstract

Are you new to deep learning and want to learn how to use it in your work? Deep learning can achieve state-of-the-art accuracy in many humanlike tasks such as naming objects in a scene or recognizing optimal paths in an environment.

The main tasks are to assemble large data sets, create a neural network, to train, visualize, and evaluate different models, using specialized hardware - often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.

In this presentation I will demonstrate how MATLAB can simplify these tasks for domain experts and enable them to apply Deep Learning techniques into their specific applications.

Biography

Paola Jaramillo is an Application Engineer at MathWorks in Eindhoven, Netherlands. She supports domain experts on the areas of Signal and Image Processing, Computer Vision and Deep Learning. Her primary interests are sensor data analytics and autonomous systems.
She holds a Master Degree in Electronic Engineering from Politecnico di Torino in Italy, and carried out a 6-month internship at IBM in Switzerland, where she worked on the deployment (FPGA) of a DSP system for structural health monitoring.
For the following 5 years she worked as a researcher at the Eindhoven University of Technology in the Netherlands, where she developed sensor-based predictive (machine learning) system to optimize energy consumption in office buildings.

Paola’s work focuses on demonstrating how the MathWorks tools and services can support the application of innovative technologies to multiple industries. She continuously participates as a presenter and exhibitor at high-tech events in the Benelux region, such as Smart Systems Industry Summit, Bits&Chips Smart Systems (Intelligent Vehicle), etc.
Recently she won a Deep Learning Hackathon with MATLAB, over other contestants using Python and TensorFlow.

{040CODERS.nl}

contact: organizers at 040coders.nl