Data science meetup | Reinforce Edition
///// Data science meetup | Reinforce Edition /////
This is a free event, We are going to start at 6pm, a bit earlier than usual, simply because we have more speakers for this special event!
6:00pm - Doors open
6:30pm - Talks
8:30pm - Pizza and soft drinks
EFFICIENT AI: BAYESIAN MACHINE LEARNING AND OPTIMAL CONTROL by PATRICK VAN DER SMAGT
Neural networks have proven themselves as excellent inference methods for learning nonlinear relationships in large data sets. But this does not suffice for systems with few or unsupervised data, such as feedback control loops. Here the merit of generative latent-variable models becomes clear. In my talk, I will explain how a Bayesian approach to neural networks can bring us towards more generally applicable artificially intelligent systems. And how adding control can create such.
This in-depth talk is intended for people who are familiar with machine-learning.
AI FAIRNESS 360 by KUSH R VARSHNEY
Machine learning models are increasingly used to inform high-stakes decisions about people. Although machine learning, by its very nature, is always a form of statistical discrimination, the discrimination becomes objectionable when it places certain privileged groups at systematic advantage and certain unprivileged groups at systematic disadvantage. Bias in training data, due to either prejudice in labels or under-/over-sampling, yields models with unwanted bias. In this talk, I will describe AI Fairness 360 (AIF360), a comprehensive open-source toolkit of metrics to check for unwanted bias in datasets and machine learning models, and state-of-the-art algorithms to mitigate such bias. We invite you to use it and contribute to it to help engender trust in AI and make the world more equitable for all.
GENERATIVE MODELING by JOZSEF NEMETH
While deep learning brought improvements in a lot of areas of computer science, generating realistic data samples is a challenging task that really requires the high representational capability of deep neural networks. Using the recently developed techniques, we can generate realistic samples like high-quality human voice or high-resolution images. At the same time, using generative models we can also learn meaningful representations of the data, that can be then used to solve other tasks, such as classification. In my presentation, I will talk about the basic concepts of generative modeling and the two most popular methods: the Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) and some of their variants. Finally, I give an overview of the wide variety of application areas. These include examples that bring quality life improvements and also about those that raise serious ethical questions about the shiny new world.