Data Scientist Romeo Kienzler shows you how to build a neural network from scratch using Python, train it, incorporate TensorFlow basics, and use Keras to quickly replicate networks.

In this video:

Deep learning frameworks like TensorFlow or PyTorch are being used with some frequency. but using such a framework hides a lot of internals which can help you understand how deep learning neural networks are designed and trained.

In this live event replay, Data Scientist Romeo Kienzler shows you how to build a neural network from scratch using Python and how to train it. Then he will introduce some TensorFlow basics to help with the task and finally, he’ll show you how to use Keras together with TensorFlow to build neural networks in a couple of minutes.

Romeo Kienzler is a Senior Data Scientist and DeepLearning and AI Engineer for IBM Watson IoT and an IBM Certified Senior Architect who spends much of his waking life helping global clients solve their data analysis challenges. Romeo holds an MSc (ETH) in Computer Science with specialization in information systems, bioinformatics, and applied statistics from the Swiss Federal Institute of Technology. He is an Associate Professor of artificial intelligence and his current research focus is on cloud-scale machine learning and deep learning using open source technologies including R, Apache Spark, Apache SystemML, Apache Flink, DeepLearning4J, and TensorFlow.

Resources for you

Discovering Data Science with Romeo Kienzler
Tackle the most difficult challenges in data science.

Subscribe by email | Subscribe on YouTube

developerWorks Live Webcasts
Live coding demos, webinars, and “ask me anythings”.

Subscribe by email | Subscribe on YouTube

Apache Spark
Create algorithms to harness insight from complex data.

Join The Discussion

Your email address will not be published. Required fields are marked *