Miklos is a senior IT professional with strong business-related skills, he has an entrepreneurial mindset combined with "the Advocate" (INFJ) personality. He started to learn software development when he was 15, therefore he studied Information Technology and Mathematics at University of Szeged. During the 3. semester he founded his first company with other fellow students where they were working during day and night as a garage firm. Later he moved to Germany to work for Audi as a software developer then switched to Volkswagen but remained as an external colleague. Then he spent 1 year in Hungary worked for the German Audi department as an external senior software developer, but he needed new challenges, therefore he accepted a position in Beijing, China at Volkswagen Group China (VGC) as an IT Consultant. Being an expat for 3 years in the capital he managed to create a Software Quality measurement platform for the IT department which controlled the software suppliers of VGC. During this period he started to be interested in data science, machine learning and its business-related opportunities. In 2015 relocated to Hungary and founded his first startup aiwebtesting.com, and started to teach at Audi Academy as an IT Trainer. In the same year he started an MBA degree at CEU (Central European University), he successfully graduated in 2017. He works as a Data Science Trainer, he delivers Big Data and Machine Learning courses at multinational companies and soon he will launch his ML-focused podcast.
Current Tricks in Deep Learning
State-of-the-art Machine Learning / Deep Learning techniques
You don't have enough data in your project? Do you have an imbalanced dataset? Do you want to know how could you you get higher precision/recall for your model? Lower RMSE? The public datasets are really nice toys, but in real life, machine learning engineers have a tough time managing their data. At the same time, is also hard to follow the latest techniques and best practices for Deep Learning...In this hands-on workshop you can learn about the latest tricks and tips for Machine Learning / Deep Learning.
The presenters will show you:
- what to do if you don't have enough data
- how to deal with imbalanced datasets
- what are the latest activation functions for Neural Networks
- what are the state-of-the-art optimizers
- what are the newest loss functions?
The presenters are not only planning to discuss the theory behind these techniques but they will also demonstrate them with source codes, so the audience can watch these techniques in practice.
This workshop is recommended for developers with at least a basic knowledge with machine learning/Deep Learning. During the coding sessions tensorflow 2.0 (mainly the keras API) with Python will be used.