New York City: https://www.datacouncil.ai/new-york-city
San Francisco: https://www.datacouncil.ai/san-francisco
ABOUT THE TALK
RNNs and LSTMs have enjoyed great success in text generation algorithms, but their use in other fields has not been as widely studied. We will discuss our experiences and progress using Recurrent Neural Networks to make predictions on arbitrary multivariate time series data. Our first study used weather data from the JFK terminal over several years using the TensorFlow framework. We will discuss the issues related to tuning and validating this model, as well as how we migrated this model into the Model Asset Exchange, which is an IBM hosted API for making predictions on data using pre-trained neural network models.
Our insight into tuning this model allowed us to provide another API via Watson Machine Learning, which is a hosted service that allows user defined data and models to be uploaded, trained, and tuned on GPU accelerated on demand hardware using simple remote API calls. We will discuss examples from the financial sector, weather prediction, and other important time series prediction use cases.
ABOUT THE SPEAKER
Jerome Nilmeier is a Data Scientist and Developer Advocate at the IBM Center for Open Source Data and Artificial Intelligence Technology (CODAIT). His duties include enablement and advocacy for IBM clients and the community at large, which includes teaching, community outreach, consulting and technical support for open source AI projects which includes Apache Spark, Tensorflow and others.Jerome has been with IBM as a data scientist since 2015. He has a BS in Chemical Engineering from UC Berkeley, a PhD in Computational Biophysics from UC San Francisco, and has carried out postdoctoral research in biophysics and bioinformatics at UC Berkeley, Lawrence Berkeley and Livermore Laboratories, and at Stanford as an OpenMM Fellow. Just prior to joining IBM, he completed the Insight Data Engineering program in late 2014.