GHOST Day: Applied Machine Learning Conference

Our Speakers

Who’s speaking

Dumitru Erhan

Staff Research Scientist & TLM | Google Brain

Dumitru Erhan is a Staff Research Scientist and Tech Lead Manager in the Google Brain team in San Francisco. He received a PhD from University of Montreal (MILA) in 2011 with Yoshua Bengio, where he worked on understanding deep networks. Afterwards, he has done research at the intersection of computer vision and deep learning, notably object detection (SSD), object recognition (GoogLeNet), image captioning (Show & Tell), visual question-answering, unsupervised domain adaptation (PixelDA), active perception and others. Recent work has focused on video prediction and generation, as well as its applicability to model-based reinforcement learning. He aims to build and understand agents that can learn as much as possible to self-supervised interaction with the environment, with applications to the fields of robotics and self-driving cars. Dumitru divides his free time between family, cooking and cycling through the Bay Area!

Piotr Mirowski

Staff Research Scientist | DeepMind

Piotr Mirowski is a Staff Research Scientist at DeepMind. He is mainly interested in reinforcement navigation-related research, in scaling up autonomous agents to real-world environments and in weather and climate modeling, but has also investigated the use of AI for artistic human and machine-based co-creation. After studying computer science in France, he obtained his Ph.D. at NYU (Outstanding Dissertation Award) under the supervision of Prof. Yann LeCun. He worked at Schlumberger Research, at the NYU Comprehensive Epilepsy Center, at Bell Labs, and Microsoft Bing on topics like epileptic seizure prediction from EEG, the inference of gene regulation networks, information retrieval and search query autocompletion, WiFi-based geolocalisation, and robotic navigation.

Ishan Misra

Research Scientist | Meta AI Research

Ishan Misra finished his Ph.D. at the Robotics Institute at Carnegie Mellon University in 2018. He has since then been working as a Research Scientist at Meta AI Research (FAIR). His main research interests are Computer Vision and Unsupervised Learning, having published multiple research papers on Self-Supervised Learning and Visual Representation, together with prominent researchers like Yann LeCun and Martial Hebert. Ishan's works have won multiple awards such as the best paper award at WACV 2014 and best paper nomination at CVPR 2021. Ishan was also a guest on the Lex Fridman Podcast and ML Street Talk.

Tomas Mikolov

Senior Researcher | Czech Institute of Informatics, Robotics and Cybernetics

Tomáš Mikolov, PhD is a Senior Researcher at the Czech Institute of Informatics, Robotics and Cybernetics in Prague. Before that, he conducted research at John Hopkins University, University of Montreal, and the Brno University of Technology from which he obtained PhD in 2012 for RNN-based language models. Later that year he joined Google Brain where he worked on neural networks applied to natural language processing problems such as representation learning (the word2vec project), neural language modeling and machine translation. During his work at Facebook AI Research, he co-authored fastText – library for text classification and representation learning. In 2020 he moved to Prague, to form a new research group at Czech Technical University focused on evolving mathematical models - the foundation of general AI.

Ivona Tautkute

Tech Lead and Senior AI Engineer | Tooploox

Ivona is an Artificial Intelligence and Machine Learning Engineer & Researcher with a focus on Computer Vision. She holds a Master's and Bachelor's degree in Mathematics from the University of Warsaw and is currently pursuing a Ph.D. in Computer Science at the Polish-Japanese Academy of Information Technology. The topic of her doctoral thesis is """"Artificial neural networks for multimodal data embeddings and classification"""". Currently, Ivona works as a Tech Lead and Senior AI Engineer at a software company Tooploox. Her area of expertise involves image recognition, object detection, object segmentation, 3D data analysis, time series prediction, and generative adversarial networks. She has published her research at major AI/ML conferences and journals, such as CVPR, IEEE Access, ICONIP and has presented her work at technology conferences in Los Angeles, New York, Lausanne, Prague, Salt Lake City and more. Ivona is also a prominent AI artist, working with photography and GANs. Her artworks are exhibited at galleries worldwide and were recently sold at a prestigious auction house Sotheby's in New York.

Wojciech Rosinski

CTO | ReSpo.Vision

Wojciech Rosinski is CTO in ReSpo.Vision, a SportTech startup aiming to revolutionize football analytics by leveraging the latest, cutting-edge AI research to watch & analyze football games providing players, scouts, managers, clubs and federations with unmatched depth of knowledge. He has extensive experience in both R&D and industry projects, where he was working on diverse projects spanning computer vision, natural language processing and tabular data. He is a Kaggle Master with 2 gold medals and multiple high finishes.

Andrew Breen

Senior Manager | Amazon TTS Research

Andrew has a B.Sc. Hons, in Physics with Computing Physics from University College Swansea, an M.Sc. (Eng.) by research from Liverpool University, and a Ph.D. in Speech Science from University College London. Andrew worked at BT Labs. on ASR, and lead teams on TTS, Avatars and multi-modal distributed systems. in 1999 he joined the University of East Anglia as a Sr. Lecturer. He join Nuance in 2001 as founder for their TTS organisation, eventually becoming Director of TTS Research, and Product Development in India and China. In 2017 he joined Amazon as the Sr. Manager for research in Amazon’s TTS organization.

Mateusz Półtorak

Senior Data Scientist | Pearson

Mateusz's great passion is modeling and mathematical approximation of complex mechanisms that rule our world. For over two years now, his work has been focusing mainly on natural language processing. Currently, he focuses on merging two worlds: world of NLP along with real word use cases, such as automatic assessment of English open-ended language tests. Privately, he worships all kinds of art.

Adam Kupryjanow

AI Applied Research Sientist | Intel

Adam is AI Applied Research Scientist in the Intel Audio team in Gdansk, Poland. He received a Ph.D from Gdansk University of Technology (GUT) in 2013. He worked on methods for speech intelligibility improvement. At Intel he was involved in many projects devoted to speech and voice processing. He developed algorithms and IP blocks like beamforming, reverb reduction, noise reduction or automatic gain control. That solutions are used in client products (laptops) and IOT (smart speakers, smart fridges, smart microwaves, kitchen robots).

view more Speakers

Conference Sessions

Training (vision) models on geodata for the protection of water reservoir ecosystems

by Paulina Knut & Zuzanna Szafranowska-Skorupko | deepsense.ai

15:30-16:00

Virtual Room 1

How to build a video classification system when you can't rely on visual features

by Karol Żak | Microsoft

16:00-16:30

Virtual Room 1

Neural radiance fields and their applications

by Marek Kowalski | Microsoft Mixed Reality & AI Lab

16:30-17:00

Virtual Room 1

Fast Synthetic Graph Generators for Graph Neural Networks

by Piotr Bigaj | NVIDIA Poland

15:30-16:00

Virtual Room 2

How AI boosted Audio Processing?

by Adam Kupryjanow | Intel

16:00-16:30

Virtual Room 2

Causal discovery in Python

by Aleksander Molak | Ironscales & Tensorcell

16:30-17:00

Virtual Room 2

Teaching Machine Learning to Children

by David Touretzky | Carnegie Mellon University

15:30-16:00

Virtual Room 3

The Consciousness of AI

by Smriti Mishra | Earthbanc

16:00-16:30

Virtual Room 3

Semantic information extraction

by Mateusz Półtorak | Pearson

16:30-17:00

Virtual Room 3

An introduction to quantum machine learning

by Paweł Gora | Quantum AI Foundation

11:00-11:30

Virtual Room 1

Accelerating AI processing on the edge

by Karol Gugala | Antmicro

11:30-12:00

Virtual Room 1

Probabilistic programming, why we need it in business settings

by Luciano Paz | PyMC-Labs

12:00-12:30

Virtual Room 1

How can we learn the structure of customer service data @Allegro?

by Aleksandra Chrabrowa | Allegro

11:00-11:30

Virtual Room 2

Tweet-Topic Classification: The Real-Life Perspective

by Mateusz Fedoryszak | Twitter

11:30-12:00

Virtual Room 2

Doctor-in-the-loop: Interactive Machine Learning in Healthcare AI

by Rachel Wities | Zebra Medical Vision

12:00-12:30

Virtual Room 2

Learning Representations for Hotel Ranking

by Ioannis Partalas | Expedia Group

11:00-11:30

Virtual Room 3

Algorithmic Balancing Models for Multi-stakeholder Recommendations

by Rishabh Mehrotra | ShareChat

11:30-12:00

Virtual Room 3

Challenges in developing Visual-Search system at Allegro

by Bartosz Ludwiczuk & Bartosz Paszko | Allegro

12:00-12:30

Virtual Room 3

A brief history of Neural TTS

by Andrew Breen | Amazon TTS Research

15:30-16:00

Virtual Room 1

Harmonic Analysis: A Complex Classification Problem

by Gianluca Micchi | IRIS Audio Technologies

16:00-16:30

Virtual Room 1

Optimizing training datasets for expressive text-to-speech synthesis

by Monika Podsiadło | Google NYC

16:30-17:00

Virtual Room 1

Towards in-silico drug design

by Marta Stępniewska-Dziubińska | NVIDIA

15:30-16:00

Virtual Room 2

Linguistic markers predict onset of Alzheimer

by Elif Eyigoz | IBM Watson

16:00-16:30

Virtual Room 2

How artificial intelligence and deep learning speed up synthesis planning in drug discovery

by Stanisław Jastrzębski | Molecule one

16:30-17:00

Virtual Room 2

Data Privacy - building ML solutions for your customers without looking at the data

by Tomasz Marciniak | Microsoft

15:30-16:00

Virtual Room 3

Deep Neural Deduplication

by Marcin Mosiolek | SII Poland

16:00-16:30

Virtual Room 3

Embracing the Range of Data Science

by Jev Gamper | Vinted

16:30-17:00

Virtual Room 3

Methods for efficient management and deployment of complex deep learning systems: a SportsTech use case

by Wojciech Rosinski | ReSpo.Vision

11:00-11:30

Virtual Room 1

How to detect silent model failure

by Wojtek Kuberski | NannyML

11:30-12:00

Virtual Room 1

Effective ML system development

by Leonard Aukea | Volvo Cars

12:00-12:30

Virtual Room 1

Bayesian Optimization with Categorical and Continuous Variables

by Vu Nguyen | Amazon

11:00-11:30

Virtual Room 2

Deep Learning for Automated Audio Captioning

by Wenwu Wang | University of Surrey

11:30-12:00

Virtual Room 2

AI for creative applications & art

by Ivona Tautkute | Tooploox

12:00-12:30

Virtual Room 2

FairPAN - Achieving fairness through neural networks

by Hubert Ruczyński | Warsaw Univeristy of Technology

11:00-11:30

Virtual Room 3

Ligands classification using sparse convolutional neural networks

by Jacek Karolczak | Poznan University of Technology

11:30-12:00

Virtual Room 3

Is music a natural language?

by Sebastian Chwilczyński | Poznan University of Technology

12:00-12:30

Virtual Room 3

CET time	DAY 1: 24/03
15:00 – 15:30	Conference opening
15:30 – 17:00	Session 1: Computer Vision	Session 2: Complex Data	Session 3: Society & AI
17:00 - 17:30	Coffee break
17:30 - 18:30	Keynote lecture 1: Visual Self-supervised Learning and World Models (Dumitru Erhan, Google Brain - San Francisco)

CET time	DAY 2: 25/03
9:30 - 10:30	Keynote lecture 2: Complex systems for AI (Tomas Mikolov, Czech Institute of Informatics, Robotics and Cybernetics - Prague)
10:30 - 11:00	Coffee break interview with Michał Kosiński, Stanford University
11:00 – 12:30	Session 4: Emerging technologies for AI	Session 5: NLP	Session 6: Recommendation & Search
12:30 - 14:00	Lunch break
14:00 - 15:00	Keynote lecture 3: Self-supervised learning for images, video, and 3D (Ishan Misra, Meta AI Research - New York)
15:00 - 15:30	Coffee break
15:30 – 17:00	Session 7: Speech & Audio	Session 8: AI in Medicine	Session 9: Data Science

CET time	DAY 3: 26/03
9:30 - 10:30	Keynote lecture 4: Skilful precipitation nowcasting using deep generative models of radar (Piotr Mirowski, DeepMind - London)
10:30 - 11:00	Coffee break interview with Jarek Wilkiewicz, Google Brain
11:00 – 12:30	Session 10: ML Ops	Session 11: ML Applications	Session 12: Student Session
12:30 - 13:00	Closing session

GHOST Day

Applied Machine Learning Conference

About Conference

Experience GHOST Day yet again in 2022!

Conference Date

24-26 March 2022

Who’s speaking

Keynote lecture

Dumitru Erhan

Keynote lecture

Piotr Mirowski

Keynote lecture

Ishan Misra

Keynote lecture

Tomas Mikolov

Ivona Tautkute

Wojciech Rosinski

Andrew Breen

Mateusz Półtorak

Adam Kupryjanow

Registration

Agenda

Conference Sessions

Training (vision) models on geodata for the protection of water reservoir ecosystems

How to build a video classification system when you can't rely on visual features

Neural radiance fields and their applications

Fast Synthetic Graph Generators for Graph Neural Networks

How AI boosted Audio Processing?

Causal discovery in Python

Teaching Machine Learning to Children

The Consciousness of AI

Semantic information extraction

An introduction to quantum machine learning

Accelerating AI processing on the edge

Probabilistic programming, why we need it in business settings

How can we learn the structure of customer service data @Allegro?

Tweet-Topic Classification: The Real-Life Perspective

Doctor-in-the-loop: Interactive Machine Learning in Healthcare AI

Learning Representations for Hotel Ranking

Algorithmic Balancing Models for Multi-stakeholder Recommendations

Challenges in developing Visual-Search system at Allegro

A brief history of Neural TTS

Harmonic Analysis: A Complex Classification Problem

Optimizing training datasets for expressive text-to-speech synthesis

Towards in-silico drug design

Linguistic markers predict onset of Alzheimer

How artificial intelligence and deep learning speed up synthesis planning in drug discovery

Data Privacy - building ML solutions for your customers without looking at the data

Deep Neural Deduplication

Embracing the Range of Data Science

Methods for efficient management and deployment of complex deep learning systems: a SportsTech use case

How to detect silent model failure

Effective ML system development

Bayesian Optimization with Categorical and Continuous Variables

Deep Learning for Automated Audio Captioning

AI for creative applications & art

FairPAN - Achieving fairness through neural networks

Ligands classification using sparse convolutional neural networks

Is music a natural language?

Honorary Patronage

Official Sponsors

Platinum

Gold

Silver

Media Partners