Practical conference about ML, AI and Deep Learning applications

Machine Learning Prague 2018

, 2018

They’re among us We are in The ML Revolution age

Machines can learn. Incredibly fast. Faster than you. They are getting smarter and smarter every single day, changing the world we’re living in, our business and our life. The artificial intelligence revolution is here. Come, learn and make this threat your biggest advantage.

Phenomenal Speakers

Practical & Inspiring Program

Friday,
Workshops

CEVRO Institut, Jungmannova 28/17, Praha 1

Registration

Room 103 Room 106 Room 203 Room 205 Room 217
coffe break

Machine Learning in the Wolfram Language

Mark Braithwaite, Wolfram

A dynamic and interactive workshop designed to take any user from a Wolfram Language beginner to being able to manipulate and use neural networks. Learn to utilise the existing library of neural networks for your own use using retraining, manipulation of those allows you to optimise them to a particular use-case. Already an expert in neural networks? Then delve into the pile of tools at hand to further edit or construct your own networks. Learn to use the Wolfram Language’s data import capabilities and Wolfram|Alpha integration to obtain data for use with the developed networks. All done within Wolfram’s notebook based development environment, allowing for easy manipulation and phased development of code.

Recommender Systems at Seznam.cz

Ondrej Javornicky, Jakub Drdak, Matej Jakimov, Stanislav Nowak; Seznam.cz

Recommender systems are probably the most visible application of machine learning. They are literally everywhere on the Internet. Most of what you can see on our website Seznam.cz is now generated by some kind of recommender system. This workshop is an introduction into basic, but still very efficient, recommending methods such as matrix factorization and logistic regression with practical tips for evaluation and how to apply them in practice on a large scale. In the second part, you will have an opportunity to play with these methods on our dataset consisting of clicks from Seznam.cz homepage.

Security in Internet of Things

Martin Bálek, Adam Hanka, Tomáš Trnka, Galina Alperovich, Martin Neznal, Vladislav Iliushin; Avast

Internet of Things (IoT) has become a hot topic in IT security. In early 2017, a vast majority of network security experts expected an increase in IoT breaches throughout the year, which underlines a very important point: nobody is immune to IoT attacks. Join us in Avast’s workshop on IoT security and experience the challenges of ML-based solutions in the security domain. We will provide an update on the current situation and guide you through the process of increasing security on your home network step by step. The main focus will be on the structure of network data and ML algorithms that can be used for device recognition and detection of anomalous behavior on IoT devices. Showing examples of network communication between clean and infected IoT devices, we will discuss the weaknesses and advantages of various ML methods within the context of IoT network traffic security, explaining the necessary steps in data preprocessing, and commenting on challenges in acquiring proper training data.

Deep Learning for Text Processing

Petr Baudis, Simon Pavlik; Rossum

Join us for our workshop and get hands-on experience with Neural Network models used in Natural Language Processing (NLP). We will introduce you to the most common Neural Nets and techniques used in NLP (bag-of-words, embeddings, CNNs and RNNs). You will get familiar with basic classification tasks performed on texts. Together we are going to build word level and character level models and use them to recognize entities in texts. We will be playing with some of the most popular tools like Keras and Tensorflow.

Cloudera Data Science Workbench (1/2)

Johny Darkwah, Gauss Algorithmic

Getting ML models running in production environments at scale can be challenging. This leads to data scientist spending more time on pipelines and cluster administration than on data analysis. In our interactive workshop, we will introduce the state of the art in terms of developing end-to-end machine learning applications. Attendees will learn how to capture and process massive volumes of structured or unstructured data from cloud object stores as a single source of truth. Once our data is ready, we will demonstrate how to leverage on-demand cloud compute resources and the processing power of GPUs for model training, all on real-world use cases and examples. Finally, we’ll learn about visualization and validation options, as well as demonstrate how to move our model to production. Participants will use the Cloudera Data Science workbench, which allows them to bring their existing skills and tools in R, Python, and Scala to securely run computations on data in Hadoop clusters. It is a self-service collaborative, scalable, and extensible platform for that lets data scientists manage their own analytics pipelines. We will also use Cloudera Altus Platform-as-a-Service to process large-scale data sets stored in cloud object store.

Lunch
coffe break

Big Data Science – Elucidation and Practice with Spark Algorithms

Stephan Sahm, Data Reply

In this workshop we are going to get hands on Apache Spark for doing Big Data Science. You will get a prepared environment with everything you need so that we can start coding some examples. Complementary to this practical part, we will look into the algorithms already implemented for spark, focussing on the crucial features which make these algorithms scale to very big data. This workshop gives you ground work in theory and practice to develop your Big Data Science with spark.

Deep Learning for Music Classification using Keras

Alexander Schindler, Vienna University of Technology
Thomas Lidy, Musimap

Deep Learning has re-entered the field of Machine Learning with a big bang. Tasks that were difficult and cumbersome to solve are now simple to implement and achieve amazingly high accuracies. Deep Learning has shown substantial impact recently also in the domain of audio recognition and music classification. This tutorial will give a general introduction to Neural Networks, Convolutional Neural Networks, plus important concepts such as (batch-)normalization, training epochs, activation, loss, optimization, pooling, dropout, model fine-tuning, etc. and a tutorial on how to apply all of this on tasks of audio and music recognition using the convenient Python Keras framework on top of Tensorflow. It will use T-SNE for visualization and also cover unsupervised learning approaches such as Autoencoders as well as Siamese Networks.

Air ticket relevancy prediction

Roman Rožník, Martin Mokrý, Mojmír Vinkler, Martin Vo; Kiwi.com

There are usually thousands of possibilities to get by plane from A to B (and back). We have to identify those that are convenient to our customers and get rid of the others. All that in startup company with biased, noisy or even missing data with little knowledge about customers. Insights into trying to do data science in crazy company. Hands on real data and real problems.

Gensim: topic modelling for humans

Radim Rehurek, Ivan Menshikh; RaRe Technologies

Dig into the Python ecosystem for data science with a hands-on workshop. This workshop focuses on the open source tool Gensim, which is used for unstructured text processing by hundreds of companies around the world. The workshop is run by the maintainers of Gensim and requires a basic understanding of Python, but no prior knowledge of Gensim itself. We’ll cover the architecture and design of Gensim, its strong and weak points, tips for performance and building robust applications. Participants are expected to bring their own laptops, to follow the hands-on exercises. We’ll focus on vector embeddings, using the popular word2vec and fasttext algorithms. Dataset downloads will be specified in advance.

Cloudera Data Science Workbench (2/2)

Johny Darkwah, Gauss Algorithmic

Getting ML models running in production environments at scale can be challenging. This leads to data scientist spending more time on pipelines and cluster administration than on data analysis. In our interactive workshop, we will introduce the state of the art in terms of developing end-to-end machine learning applications. Attendees will learn how to capture and process massive volumes of structured or unstructured data from cloud object stores as a single source of truth. Once our data is ready, we will demonstrate how to leverage on-demand cloud compute resources and the processing power of GPUs for model training, all on real-world use cases and examples. Finally, we’ll learn about visualization and validation options, as well as demonstrate how to move our model to production. Participants will use the Cloudera Data Science workbench, which allows them to bring their existing skills and tools in R, Python, and Scala to securely run computations on data in Hadoop clusters. It is a self-service collaborative, scalable, and extensible platform for that lets data scientists manage their own analytics pipelines. We will also use Cloudera Altus Platform-as-a-Service to process large-scale data sets stored in cloud object store.

from
Party
La Loca Music Bar, Odborů 278/4, Praha 2

Saturday,
Conference day 1

Rudolfinum, Alšovo nábřeží 12, Praha 1

Registration

Welcome to ML Prague 2018

Magic in the Machine

Anna Ukhanova, Google (CH)

Google’s ongoing research in AI is what powers many of the products being used by hundreds of millions of people a day - from Translate to Photo Search to SmartReply for Inbox. One of the things that enables these advances is the extensive collaboration between the Google researchers in our offices across the world, all contributing their unique knowledge and disseminating ideas in state-of-the-art Machine Learning technologies and techniques in order to develop useful tools and products.

While we aim to provide everyday users with useful and innovative products, it is also important that we expand access to AI for other companies to use in their products as well.

In this talk Anna Ukhanova will speak about Google's approach to AI, collaborations with academia, our open-sourced Machine Learning platform TensorFlow and Cloud Machine Learning.

Symbolic Neural Networks & Automated Machine Learning in the Wolfram Language

Etienne Bernard, Wolfram Research (USA)

As part of the Wolfram Language, we recently developed an original machine learning framework that can be used by both beginners and experts in the field. The framework includes a symbolic and functional neural network framework, a repository of pre-trained networks, and fully automated machine learning functions. I will give an overview of this framework, demonstrate its capabilities, and talk about the scientific and technical solutions used under the hood.

Really Automating Machine Learning

Charles Parker, BigML (USA)

Machine learning practitioners would all love a method of providing the best classifier given some data, with no algorithm selection or parameter tuning required. New techniques in the research literature, especially Bayesian parameter optimization, hold the promise of being able to do exactly this, but having a method for doing a thing is very different to actually doing it. In the first half of this talk, I'll discuss the nuts and bolts of machine learning automation, including how to know when we've actually done it right. In the second half, I'll talk about why “automation” might only be a poor substitute for our actual goal.

Lunch

Personal Shopping Assistants for Conversational Commerce

Amit Srivastava, eBay (USA)

Shoppers are increasingly engaging in new modes of interaction such as messaging and voice. To provide our customers with a personalized experience across multiple engagement endpoints, eBay has embarked on a journey to develop AI-powered personal shopping assistants. In this talk, we will highlight the many ways we are leveraging big data and machine learning to enable conversational commerce at eBay.

Near-Optimal Interactive Recommender Systems

Branislav Kveton, Adobe Research (USA)

Recommender systems interact repeatedly with their users. For instance, Google’s search engine processes billions of search queries daily. This gives rise to the exploration-exploitation dilemma. The recommender system may decide to exploit, recommended the best choice under its potentially-suboptimal current model of the user; or to explore, recommend suboptimal choices under the current model that allow the algorithm to improve its model, for instance from the clicks of the user. Multi-armed bandits are a principled way of dealing with the exploration-exploitation dilemma. In this talk, we introduce stochastic multi-armed bandits and show how to use them to design real-world recommender systems. These problems have multiple challenges. The space of recommended content is typically exponentially large, there are L^K lists of K web pages out of L. In addition, the responses of users are subject to strong biases. In particular, the user often does not click on the web page because other recommended web pages are better, not because this particular web page is bad.

Dimensionality Reduction for Guaranteed Display Advertising

Antonín Hoskovec, Seznam.cz (CZ)

Guaranteed display advertising has been an area of vivid interest over the recent years. Advertising agencies want to be able to make a contract with advertisers for a certain number of impressions and then to honor it. Guessing the number of impressions with a given target audience then becomes a necessity.

Coffee Break

Deep Learning is Revolutionizing Artificial Intelligence

Sepp Hochreiter, Institute of Bioinformatics, Johannes University of Linz (AT)

Deep Learning has emerged as the most successful field of artificial intelligence with overwhelming successes in industrial speech, language and vision benchmarks. I invented LSTM recurrent neural networks, which evolved into a key technology in different AI fields like speech, language, and text analysis.

We use LSTM for natural language processing in collaboration with companies like Zalando and Bayer, e.g. to analyze fashion blogs or twitter news related to health. In the AUDI Deep Learning Center and in collaboration with NVIDIA we apply Deep Learning to advance autonomous driving. With Deep Learning we won the NIH Tox21 challenge, predict biological effects of drug candidates from their chemical structure and from high content imaging.

In current research we analyze convergence properties of generative adversarial networks (GANs) using stochastic approximation (cf. TTUR). Further we investigate self-normalizing networks, which automatically converge to their optimal learning conditions (cf. SELUs). Most recently, we developed a new reinforcement learning method, which outperforms Monte Carlo Tree Search and other RL methods on delayed reward problems. This new method has a potential to initiate a paradigm shift in reinforcement learning.

The Alexa Prize Socialbot

Jan Pichl, eClub Prague (CZ)

Alquist is one of the three chatbots which were selected as the Alexa Prize finalist. Its task is to maintain a coherent and engaging conversation with a user about popular topics (movies, sports, news, music, etc.), and it uses a combination of generative and retrieval approaches to balance the advantages of both of the methods. It has been developed for more than a year by a group of 5 students. We will describe the Alquist architecture with all the NLP techniques we used as well as all the obstacles we encountered during the Alexa Prize competition.

Prospects in Quantum Enhanced Machine Learning

Jacob Biamonte, Skolkovo Institute of Science and Technology (RUS)

Quantum mechanics offers tantalizing prospects to accelerate and improve certain machine learning tasks. Can these prospects be born out in practice? With rapid advancements in quantum processor technology, a vast international community has quickly formed to investigate the uses of current (medium sized and noisy) quantum processors. Some of the results look promising but challenges still remain. So exactly when will we see a quantum machine learning revolution?

Coffee Break

Putting Research Into Practice: The Good, the Bad and the Ugly

Radim Řehůřek, RaRe Technologies (CZ)

Lessons from a decade of building advanced ML solutions for companies like Amazon, Hearst or Autodesk, maintaining open source software, running a Student Incubator and launching innovative AI products. This talk focuses on the journey of standing on your own two feet when it comes to applied R&D. How did we combine academia, open source and industry while following our dreams?

GDPR & ePrivacy rule as an EU gift to non-EU technological competitors

Karel Vaculík, Gauss Algorithmic (CZ)

Ethical and moral aspects of research were always on the table in democratic countries, but when governments fail to find the line between meaningful regulations based on threat analysis and replace it with ideology, science is on the retreat. GDPR and ePrivacy regulation might be such direct threats for the substantial part of the AI research and industries in EU.

from
from

Party

Royal, Vinohradská 48, Praha 2

Sunday,
Conference day 2

Rudolfinum, Alšovo nábřeží 12, Praha 1

Doors open

Computer vision technology in Konica Minolta’s Care Support Solution

Satoshi Kondo, Konica Minolta (JAP)

Konica Minolta launched Care Support Solution, a monitoring system for nursing care workflow innovation, in 2016. The Sensor Box, which is the core of the system, performs 24-hour monitoring using near-infrared and microwave sensors. If a patient sits up on the bed, leaves the bed, falls down, or falls out of the bed, nursing staff are notified via a smartphone with video display. The staff can also use their smartphones to input care records or vital-sign data on the spot and share them instantly. By providing one-stop total innovation that covers both the nursing care frontlines and administrative work such as record keeping, the Care Support Solution offers greater efficiency for the entire nursing care operation. In this talk, the concept of the Care Support Solution and the computer vision technologies used in the system are introduced.

Open Science challenges for Machine Learning in Healthcare

Leonie Mueck, Public Library of Science (UK)

Being open and transparent about scientific developments and discoveries is important for any discipline. In healthcare it is crucial: given their huge societal impact, openness can make or break the success of new therapies and drugs. Applying machine learning methods in healthcare poses new challenges to openness, for example due to the black-box nature of algorithms or due to privacy concerns. In this talk, I will give a brief overview over how machine learning methods are being applied in clinically relevant settings, what the open science challenges are and how possible solutions may look like.

Deploying text-classification RNNs in a multinational bank

Vlado Boža, CEAi (CZ)

One part of the anti money laundering process is a background check of the client to determine whether the client has been engaged in any risky or illegal activity. This was done mostly by searching manually news databases and reading returned articles. Vlado Boza will present how Merlon Intelligence helps automate this process by implementing a solution using recurrent neural networks and also how it has coped with limited availability of training data.

Coffee Break

Calibration of the web browsing traffic

Jonáš Amrich, Jumpshot (CZ)

Jumpshot has a large datastream of web browser activities of an international panel. To produce accurate estimates of aggregate metrics, we need to calibrate from our data, a fraction of the actual web traffic, to its true value for any particular country, platform, domain and day. For precise calibration, correction of bias of our panelists is inevitable task that traditionally requires knowledge about both panelists and the whole population, which is not available in our case. Popular approach is to utilize sophisticated learning methods that produce phenomenological models with high accuracy but low interpretability. Contrary to that, our story shows that simpler but mathematically sound microscopical model can outperform such models and provide more clarity at the same time.

Social Good at Cloud Scale

Michael Lanzetta, Microsoft (USA)

Deep Learning has the chance to be a massive force for good in the world, and I’ll discuss some of our projects in that area: Finding disaster victims using facial recognition, helping quantify the impact of illegal mining in Ghana, and tracking endangered species. We’ll take a look at the problems, their solutions, how we scale out model training on the cloud, and how we deploy solutions in the cloud for operation at scale – and I’ll point you to the open-source repositories so you can do it yourself.

Machine Learning for Better Understanding: Improving the Efficiency of a Data Center

Karel Macek, DHL (CZ)

DP DHL has 500K employees, making it one of the largest companies worldwide. Their business is related to massive data processing, supported by DHL ITS with its 4000+ employees. How can machine learning make their daily jobs easier? What information helps them understand ongoing issues better? What can they do to anticipate difficult periods of operation? Let us share some insights from our own experience in this domain.

Lunch

SpaceKnow: Using deep learning to monitor Earth from space

Michal Reinštein, SpaceKnow (CZ)

In this talk we’ll explore how we combine machine learning algorithms and computer vision techniques with the latest cloud technologies for semantic segmentation, object detection and classification on multi-spectral multi-resolution satellite images. We’re developing a proprietary, scalable platform and frameworks enabling reproducible multi-GPU training and massively parallelized prediction, aiming to deliver global geospatial intelligence. Our production system is a single-point access to the world’s largest satellite providers, including DigitalGlobe, Airbus, Planet, and Urthecast, offering real-time, on-demand analytics through APIs and an web application.

Joyful Machine Learning Over Telco Data

Jan Romportl, O2 Czech Republic (CZ)

Machine learning is daily bread for the Data Science team at O2 and it has been applied in many projects and data products, both for internal and external business clients. However, some of these ML efforts stand out by being extremely rewarding for us not necessarily in terms of business success, but in terms of pure joy of trying something that not many in the telco domain have tried before, and perhaps seeing some fascinating or surprising results. This talk will thus be exactly about such cases.

Taking down ML pain points

Marek Modrý, CEAI (CZ)

At CEAi, we don’t like repetitive or tedious work. On the other hand, we like to build cool stuff that simplifies our lives. That's why we decided to get rid of some pain points that are pervasive in machine learning. “I trained a model 6 months ago … which data did I use again? What parameters did I try?” Don’t tell my boss but let’s be honest: usually, I can’t remember. Hence my motivation to talk about our effort to build a system that facilitates reproducibility, automates validation, testing, auditing and continuously searches for the next best model. In addition to this, the system will use active learning strategies to shorten the total time to model deployment and reduce load on annotator pools.

Coffee Break

Panel discussion

Sepp Hochreiter, Jacob Biamonte, Radim Řehůřek, Michael Lanzetta

Closing Remarks

Have a great time Prague, the city that never sleeps

A unique capital where you can breathe centuries of history at every corner. We’ll take a tour to explore the sights, invite you to taste the best pivos (that’s beer in Czech) and bring you back to the present by clubbing with you the whole night!

Impressive Venue

Now the seat of the Czech Philharmonic, the Rudolfinum is a Neo-renaissance building associated with music and art since 1885 and only used for truly outstanding purposes. The comfort, acoustics, and design makes it the greatest venue in the whole of Europe and it’s available for us.

Conference Hall

Rudolfinum
Alšovo nábřeží 12, Praha 1

Workshops

CEVRO Institut
Jungmannova 28/17, Praha 1

Now or never Tickets

Early Bird

Sold Out

  • Conference days € 200
  • Only workshops € 100
  • Conference + workshops € 290

Standard Ticket

Sold Out

  • Conference days € 240
  • Only workshops (sold out) € 120
  • Conference + workshops (sold out) € 350

Late Ticket

Sold out

  • Conference days (sold out) € 280
  • Only workshops (sold out) € 140
  • Conference + workshops (sold out) € 410

What You Get

  • Practical and advanced level talks led by top experts
  • 2 parties in the city with people from around the world. Let’s go wild!
  • Traditional Czech food throughout the conference

We Know That A Little Party Never Killed Anybody

Friday party 19:00

La Loca Music Bar
Odborů 278/4, Praha 2

Saturday party 19:00

Royal
Vinohradská 48, Praha 2

Our Attendees What they say about ML Prague

Thank you to Our Partners

Platinum Partner

Gold Partners

Silver Partners

Party Partner

Media Partners

Become a partner

Happy to help Contact

If you have any questions about Machine Learning Prague, please e-mail us at
info@mlprague.com

Organizers

Šárka Štrossová
sarka@mlprague.com

Jiří Materna
jiri@mlprague.com