Speaker Details

Nick Bourdakos

IBM

Nick is a developer advocate at IBM Watson in NYC. His expertise is in machine learning, mainly deep learning applied to Computer Vision problems. He started out as an Android developer, but also does Swift, Python and JavaScript / React development.

Realtime Object Detection in the Browser with Tensorflow.js

Hands-on Lab
Big Data & Machine Learning

Whether you are counting cars on a road or people stranded on rooftops in a natural disaster, there are plenty of use cases for object detection. Often times, pre-trained object detection models do not suit our needs and we need to create our own custom models. How can we utilize machine learning to train our own custom model without substantive computing power and time? Answer: Watson Machine Learning. How can we leverage our custom trained model to detect object’s, in real-time, with complete user privacy, all in the browser? Answer: TensorFlow.js. In this workshop, you will create a web app that does just that. You will learn how to create an IBM Cloud Object Storage instance to store your labeled data. Once your data is ready, you will learn how to spin up a Watson Machine Learning instance to train your own custom model on top-of-the-line GPUs. After your model has completed training, you can simply plug the TensorFlow.js model into your react application. At the end of this workshop, you should understand how to: - Label data that can be used for object detection - Use your custom data to train a model using Watson Machine Learning - Detect objects with TensorFlow.js in the browser

Scheduled on Tuesday from 09:30 to 12:30 in BOF 2

Deep Learning
Computer Vision
TensorFlow

Understanding What Artificial Intelligence Actually Sees

Conference
Big Data & Machine Learning

Many call artificial intelligence (AI) a “black box”, and it kinda is! One of the biggest problems of AI is that it’s incredibly difficult to understand how the data is being interpreted. In this talk we'll pull back the curtain and find out what AI actually sees. We'll also learn how to: - be mindful of this knowledge when we actually train our models. - use open source tools to train our very own custom object detection model with minimal training data. - use this model in a real-time web app.

Scheduled on Wednesday from 17:50 to 18:40 in Room 7

Deep Learning
Computer Vision
TensorFlow

Talks by tracksTalks by session typesList of SpeakersSchedule