Deep Learning in the Cloud for Image Classification and Object Recognition with Convolutional Neural Networks using MATLAB

During this workshop, you will learn how to develop deep learning applications for computer vision using practical examples (though the learnings can be applied to other applications such as signal processing, speech recognition, etc.) that run either in your computer, your GPU, a cluster or in the cloud. Moreover, you will learn how to auto-generate portable and optimized CUDA code from the MATLAB algorithm, which can then be cross-compiled and deployed to an embedded GPU. Deep Learning with MATLAB Workshop.

Demo Station 1: Deep Learning with MATLAB (Opened all day at MathWorks Booth)

Visit this demo station and discover how the MATLAB framework makes Deep Learning easy and accessible. We’ll showcase how to build and train deep neural networks, import pretrained models from TensorFlow and Caffe, and make use of the most recent architectures (Alexnet, VGG, GoogLeNet, ResNet) to solve classification and regression problems, such as figuring out the drivable area in a city environment. Moreover, we will demonstrate how to convert a trained model to CUDA in order to run the network on embedded GPUs, such as the NVIDIA Jetson TX2 development kit.

If you are interested in having hands-on exposure to MATLAB’s framework for Deep Learning, considering attending our Deep Learning with MATLAB Workshop on November 15th.

Demo Station 2: Machine Learning and Big Data with MATLAB (Opened all day at MathWorks Booth)

Visit this demo station and discover the different tools that MATLAB provides to tackle Machine Learning and Big Data challenges and work to deliver insights from data sets of all sizes. Learn how MATLAB provides numerous capabilities for processing big data that scales from a single workstation to compute clusters, including accessing data from Hadoop Distributed File System (HDFS) and running algorithms on Apache Spark. MATLAB is certified for use with the Cloudera Enterprise Data Hub and the Hortonworks Data Platform.

Demo Station 3: Streaming Analytics with MATLAB (Opened all day at MathWorks Booth)

In this demo station, we will show a full workflow from the development of machine learning models in MATLAB to deploying it to work with a real-world sized problem running on the cloud. The demo will showcase the use of MATLAB models against distributed streams of data from Apache Kafka. The workflows for the design and implementation of machine learning models supports the easy query of these big datasets via distributed SQL query engines such as Presto and scaling of the analytic models on the cloud.

Engineering analytics for predictive health applications by Arvind Hosagrahara (Theatre 19)

Join Arvind's talk.

Demo Station 1: Deep Learning with MATLAB (Opened all day at MathWorks Booth)

See demo description on Thursday's schedule.

Demo Station 2: Machine Learning and Big Data with MATLAB (Opened all day at MathWorks Booth)

See demo description on Thursday's schedule.

Demo Station 3: Streaming Analytics with MATLAB (Opened all day at MathWorks Booth)

See demo description on Thursday's schedule.