An Introduction, and 1-2 Lectures on neural networks and machine learning technologies and their importance in economy and in general.
We are going to draw on what we have discussed in previous coloquiu on AI, what deep learning ist suppose to be, what algorithms are subsumed by this and talk about some of these technologies in more detail.
Title: Astonishing phenomena.
Summary: On previous colloquia on AI at PhenCoCo, examples for AI creating 'art', like the nvida-alogrithm, an image processing engine, which can transform rudimentary pictures into beautiful landscapes, or the sound aiva engine, creating elaborate synfonies not unlike movie soundtracks.
Title: Machine Learning (ML) fundamentals and types of ML algorithms
Outline Machine Learning (ML):
Introduction, definitions, classic programming vs ML, fundamental concepts, common terms. Types of ML algorithms: criteria categorisation, supervised learning, unsupervised learning, reinforcement learning, classification, regression, common algorithms, use cases, examples. The machine learning process, methods, applied examples, cost function, gradient descent. Fundamentals of Neural Networks.
Machine learning (ML) is the science of getting computers to learn to act, based on data, and without explicitly programming the rules. In the past years, machine learning provided us with a wide range of applications such as effective web search, speech recognition, autonomous driving, advanced image recognition and processing capabilities, and allowed achievements previously thought impossible (Deep Learning, AlphaGo Zero). Most of us use ML several times in our daily lives without even noticing it. The current presentation aims to clarify the fundamental concepts of the matter by categorising, organising and presenting the available information and to provide insight on the fundamental ML processes.
About the speaker:
Joaquin holds an Electronics Engineering Degree of the University of Rosario , Argentina. As DAAD scholarship holder and research scientist at the IFR in the University of Brunswick he dedicated to computer vision, autonomous driving and signal processing. He subsequently engaged in the field of Wind Energy as a Development Engineer for several years working on electronics, modelling, simulation and data analysis.
He lives currently in Berlin and works independently in projects ranging from renewable energy to modelling and simulation.
- star craft & ai: https://www.theverge.com/2019/1/24/18196135/google-deepmind-ai-starcraft-2-victory
- gradient descent (finding the right optimum - maxima/minima)
- underfitting and overfitting: when neural networks get imbalanced, under- and overfitting leads to an ovrerabundance or lack of percision, which distortes the optimal result for the task at hand. Reserving some training data for tests can help to avoid this distortion.
- Is underfitting and bias the same or do the concepts just overlap? To call underfitting bias, even though it can be parallelized, is not as neutral. It therefore depends on the focus one wants to put in language.
- example for a popular convolutional neural network in use: CNN Mobile Net V2
Data use permission:
When you come to the event and/ or leave your email – or other messenger-contact – with us, you have done this with the permission to invite you again.
Undo data use permission:
If you have received an e-mail but want to undo your data permission, or have any trouble with the way it is realised, please let us know. You will not get an invitation again, and we will try to cater to your needs as much as possible, if you have comments on details that would make the conduct more agreeable to you.