26-28 November, 2019, Vilnius
Conference Starts in:
A Practical-ish Introduction to Data Science
Data Science has been described as the sexiest job of the 21st Century. But what is Data Science? And what has Machine Learning got to do with all of this?
In this talk, Mark will share insights and knowledge that he has gained from building up a Data Science department from scratch.
Deconstructing Deep Learning
In this session attendees can expect a mathematics and jargon free introduction to Deep Learning!
1. Mark will start by defining the general principles and theory behind Deep Learning and Artificial Neural Networks.
2. Next Mark will demonstrate how Deep Learning can be utilised for Image Processing, by taking a look at an implementation of a Convolutional Neural Network (CNN).
You can AI like an Expert
The talk will discuss Wolfram’s progress towards an entirely automated workflow for machine learning that makes it possible for anyone who can code to make use of AI methods.
The talk will assume no knowledge of machine learning and will introduce key concepts before showing how to use the Wolfram Language to create advanced predictors from scratch, in seconds. Use will be made of the Wolfram Language functions Predict and Classify which automate the process of data encoding, feature extraction, method selection, training, end decoding. The net result is a single function that produces a ready-to-use classifier or predictor, directly from raw data.
Deep Learning for Lazy People... Neural Architecture Search with Automated Machine Learning
Deep Learning models are great, but choosing the right architecture is not easy. Many times, the easiest way of getting the best architecture is just by trying.
It would be nice to have a clairvoyant that is able to tell us the best architecture, right? We cannot have a clairvoyant but we have tools, like Automated Machine Learning, that are able to find the best architectures just with a few lines of code.
Predicting the Moment of Birth using Sensor Data in Dairy Cows
Stillbirth, defined as calves that die during unobserved birth is often seen as an indicator of lowered animal welfare in dairy cows. Sensors have been proposed as a tool to support dairy farmers but accurate calving prediction models are often lacking. In this session, a machine learning data pipeline will be described using the spark ML framework. Heavy lifting and feature preparation for sensor data from 1331 cows on 8 herds from 21 days before until the day of calving was performed using sliding windows and time series analysis.
Knowledge and AI Powering Microsoft & Office 365 Products
Knowledge, Data and AI have been reshaping the way we live and work for the past few years, and the fact is that this is just the beginning.
Everyone has been using AI-and-knowledge-infused products and services every day, sometimes in ways that may not seem obvious. One of David’s goals in this session will be to explain how these non-obvious scenarios are being powered with Knowledge and AI (and how/why, through improvements in technology, these will just get better).
Practical Data Science - How to Track Your Development Process with DVC
Datacentric applications utilising machine learning models have evolved into common solutions. Many projects however still suffer from a lack of good patterns and practices, when developing such powerful technologies.
Digging down into the nitty-gritty details, we explain how you can use DVC to version all parts of your projects: From the dataset, over gluecode up to the model itself. But wait, there’s more! We show you code that covers the full development cycle, including experiments and reproducability, as well as release and deployment of your model to machines in the wild.
(Un)ethical Artificial Intelligence: How to Keep the AI Fair for Everyone
This presentation highlights the current ethical problems that we face while building artificial intelligence solutions. The artificial intelligence systems based on machine learning algorithms are entering our products at an increasing rate. Unfortunately, keeping these systems fair is hard and a lot of hidden biases enter the models, even if the developers had the best intentions. We will investigate some of the failures of the AI systems and explore ways how to keep them fair for everyone.
Secure IoT Command, Control, and Exfil with Apache MiNiFi
Apache MiNiFi is a lightweight application which can be deployed on hardware orders of magnitude smaller and less powerful than the existing standard data collection platforms. Not only can this data be prioritized and have some initial analysis performed at the edge, it can be encrypted and secured immediately. Local governance and regulatory policies can be applied across geopolitical boundaries to conform with legal requirements.
Big Data Legal Issues. GDPR and Contracts
Big Data legal issues. GDPR and contracts.
How can we use the Big Data legally?
What are the legal components of Big Data?
What about GDPR and Big Data?
Contracts on big data and for data analisys
Predicting Cryptocurrency Exchange Rates with Stream Processing, Social Data and Online Learning
In a recent project, iunera sought to determine if it is possible to predict crypto currency exchange rates by utilizing social data from Twitter. Tim will talk about their experiences and describe how they leveraged online learning in conjunction with social data to determine if they are able to predict future currency exchange rates.