- Видео 74
- Просмотров 23 811
GHOST Day: AMLC
Добавлен 2 окт 2020
GHOST Day: AMLC is a two-day conference dedicated to applied machine learning. During our conference, we will have the chance to listen to speakers from all around the world, working in top tech companies, start-ups and universities. Our agenda is divided into 3 parallel paths, each of them containing a few hours of lectures with special focus on different areas of machine learning. We encourage participants from all backgrounds to take part in our conference, we will definitely have topics for everyone!
The conference is organized by Group of Horribly Optimistic STatisticians (GHOST), a machine learning research student group operating at Faculty of Computing and Telecommunications, Poznań University of Technology. The group gathers talented students and graduates interested in deepening their understanding of machine learning algorithms.
The conference is organized by Group of Horribly Optimistic STatisticians (GHOST), a machine learning research student group operating at Faculty of Computing and Telecommunications, Poznań University of Technology. The group gathers talented students and graduates interested in deepening their understanding of machine learning algorithms.
Exoplanet Discovery with Machine Learning | NASA's Hamed Valizadegan at GHOST Day: AMLC
Abstract:
The Kepler and TESS missions have yielded an astounding 100,000 potential transit signals, paving the way for an intricate process of distillation to identify viable exoplanet candidates. In response to this formidable challenge, we introduce ExoMiner, a groundbreaking deep neural network meticulously designed for the classification of transit signals in the search for exoplanets. ExoMiner played a pivotal role in validating and authenticating 301 previously undiscovered exoplanets. This keynote voyage commences with a sweeping overview of the captivating realm of exoplanetary exploration. As we delve into the heart of our presentation, we embark on an exploration of the distinct...
The Kepler and TESS missions have yielded an astounding 100,000 potential transit signals, paving the way for an intricate process of distillation to identify viable exoplanet candidates. In response to this formidable challenge, we introduce ExoMiner, a groundbreaking deep neural network meticulously designed for the classification of transit signals in the search for exoplanets. ExoMiner played a pivotal role in validating and authenticating 301 previously undiscovered exoplanets. This keynote voyage commences with a sweeping overview of the captivating realm of exoplanetary exploration. As we delve into the heart of our presentation, we embark on an exploration of the distinct...
Просмотров: 117
Видео
Real-World Computer Audition: An Interstellar Experience | Björn W. Schuller, GHOST Day: AMLC
Просмотров 2545 месяцев назад
Abstract: In this talk, we will voyage into uncharted territories where the latest in artificial intelligence converges with computational audio understanding and generation. It will unveil how cutting-edge deep learning techniques propel Computer Audition into unexplored dimensions. From unraveling complex audio patterns in healthcare diagnostics to orchestrating audio composition, it illumina...
Neural Approaches to Personalized Search | Gabriella Pasi at GHOST Day: AMLC
Просмотров 835 месяцев назад
Abstract: In the past few years there has been an increasing interest in the application of Deep Learning techniques to various Information Retrieval tasks, among which Personalized Search. This lecture will present an overview of the research undertaken in Gabriella Pasi's research lab, related to the definition of neural approaches to personalise search. In particular, three contributions wil...
Nash Learning with Human Feedback | Michal Valko from META at GHOST Day: AMLC
Просмотров 3725 месяцев назад
Abstract: Reinforcement learning from human feedback (RLHF) is a go-to solution for aligning large language models (LLMs) with human preferences; it passes through learning a reward model that subsequently optimizes the LLM's policy. However, an inherent limitation of current reward models is their inability to fully represent the richness of human preferences and their dependency on the sampli...
Recovering Cosmic Microwave Background with Neural Networks | Laura Bonavera at GHOST Day: AMLC
Просмотров 915 месяцев назад
Abstract: The Cosmic Microwave Background (CMB) is a remnant radiation of the Big Bang, which is thought to mark the origin of the universe. The CMB anisotropies provides fundamental information about cosmology and on the initial conditions and the energy contents of the Universe. Therefore, it is very important to measure them with the highest precision, implying a very precise recovery of the...
Future of AI: Expert Panel with J. Stefanowski, R. Kroplewski & W. Duch | GHOST Day: AMLC
Просмотров 2656 месяцев назад
Abstract: Following the initial excitement about AI’s “silver bullet” potential, concerns about its associated risks start to grow. How can we balance lowering the probability of these risks while avoiding inhibiting the growth of AI? What steps need to be taken, and by whom-us, big companies, or governments? What defines "Responsible AI," and how can we achieve it? Our experts will answer thes...
Scalable Training and Inference, Mateusz Malinowski | GHOST Day: AMLC 2023
Просмотров 102Год назад
Abstract: Current computer vision research mainly focuses on individual images or short videos due to the challenges associated with processing longer videos. However, experience and reasoning often occur across multiple temporal scales ranging from milliseconds to days. This talk has three parts. In the first part of the talk, I will briefly present various achievements in the multimodal space...
Walk this way: AI-powered customer journey, Konrad Banachewicz | GHOST Day: AMLC 2023
Просмотров 128Год назад
Abstract: Analysing the customer journey in an e-commerce website is essential for understanding the user's experience and identifying areas for improvement. The customer journey refers to the path a user takes from initial engagement with a website or product to final purchase; placing an ad, personalised recommendations experience, safe and secure communication, delivery options - all those c...
Representation and Quantification of Uncertainty in ML, Eyke Hüllermeier | GHOST Day: AMLC 2023
Просмотров 161Год назад
Abstract: The notion of uncertainty has recently drawn increasing attention in machine learning research due to the field's burgeoning relevance for practical applications, many of which have safety requirements. This talk will address questions regarding the representation and adequate handling of (predictive) uncertainty in (supervised) machine learning. The distinction between two important ...
Bayesian Optimization with Categorical and Continuous Variables, Vu Nguyen @ Amazon | GHOST Day 2022
Просмотров 271Год назад
Abstract: "Bayesian optimization (BO) has demonstrated impressive success in optimizing black-box functions. However, there are still challenges in dealing with black-boxes that include both continuous and categorical inputs. I am going to present our recent works in optimizing the mixed space of categorical and continuous variables using Bayesian optimization [1] and how to scale it up to high...
Deep Learning for Automated Audio Captioning, Wenwu Wang @ University of Surrey | GHOST Day 2022
Просмотров 248Год назад
Abstract: Automated audio captioning (AAC) aims to describe an audio clip using natural language and is a cross-modal translation task at the intersection of audio processing and natural language processing. Generating a meaningful description for an audio clip not only needs to determine what audio events are presented, but also needs to capture and express their spatial-temporal relationships...
Deep Neural Deduplication, Marcin Mosiolek - AI Architect @ SII Poland | GHOST Day: AMLC 2022
Просмотров 162Год назад
About the speakers: Marcin is an AI Architect with over ten years of experience in a wide range of commercial machine learning projects, mainly related to natural language processing and computer vision. He converts the latest academic research into operating products in his daily job rather than Jupyter Notebooks only. After working hours, Marcin enjoys strong winds and rough seas while kitesu...
Linguistic markers predict onset of Alzheimer's disease, Elif Eyigoz @ IBM | GHOST Day: AMLC 2022
Просмотров 2882 года назад
This presentation was given during GHOST Day: AMLC 2022. About the speaker: Elif Eyigoz, PhD works as a Research Staff Member at IBM Watson NY. She is a member of the Healthcare and Lifesciences research group. Elif has an exceptional multi-disciplinary background in Philosophy (BA), Cognitive Science (MA), Linguistics (MA), and Computer Science (MS and PhD). She joined IBM in 2014. In 2020 she...
Towards in-silico drug design by Marta Stępniewska-Dziubińska @ NVIDIA | GHOST Day: AMLC 2022
Просмотров 1972 года назад
Presentation given during GHOST Day: AMLC 2022. About the speaker: Marta is a Software Engineer at NVIDIA, working on deep learning models for computer vision and drug discovery. She started working with ML during her PhD, for which she built deep neural networks for structure-based drug discovery. Afterwards she decided to turn to industry and used her skill-set for computer vision problems. S...
Optimizing training datasets for expressive text-to-speech synthesis by Monika Podsiadło @ Google
Просмотров 2042 года назад
Presentation given during GHOST Day: AMLC 2022. About the speaker: Monika Podsiadło leads Text to Speech Applied Research at Google New York with over 10 years of experience in the field. Her work is centered around managing a team focused on prosody, few-shot learning, and cross-lingual modeling. Before that, together with her team, she launched over 200 TTS voices in 30 languages, productioni...
Harmonic Analysis: A Complex Classification Problem - Gianluca Micchi IRIS Audio Technologies | GD22
Просмотров 572 года назад
Harmonic Analysis: A Complex Classification Problem - Gianluca Micchi IRIS Audio Technologies | GD22
Self-supervised learning for images, video, and 3D - Ishan Misra, Meta | GHOST Day: AMLC 2022
Просмотров 6342 года назад
Self-supervised learning for images, video, and 3D - Ishan Misra, Meta | GHOST Day: AMLC 2022
Probabilistic programming, why we need it in business settings by Luciano Paz @ PyMC-Labs
Просмотров 602 года назад
Probabilistic programming, why we need it in business settings by Luciano Paz @ PyMC-Labs
Accelerating AI processing on the edge - Karol Gugala, Antmicro | GHOST Day: AMLC 2022
Просмотров 1032 года назад
Accelerating AI processing on the edge - Karol Gugala, Antmicro | GHOST Day: AMLC 2022
An introduction to quantum machine learning by Paweł Gora @ Quantum AI Foundation
Просмотров 1622 года назад
An introduction to quantum machine learning by Paweł Gora @ Quantum AI Foundation
Visual Self-supervised Learning and World Models - Dumitru Erhan, Google | GHOST Day: AMLC 2022
Просмотров 1902 года назад
Visual Self-supervised Learning and World Models - Dumitru Erhan, Google | GHOST Day: AMLC 2022
Causal discovery in Python - Aleksander Molak, Lingaro | GHOST Day: AMLC 2022
Просмотров 5 тыс.2 года назад
Causal discovery in Python - Aleksander Molak, Lingaro | GHOST Day: AMLC 2022
Fast Synthetic Graph Generators for GNNs - Piotr Bigaj, Nvidia | GHOST Day: AMLC 2022
Просмотров 1332 года назад
Fast Synthetic Graph Generators for GNNs - Piotr Bigaj, Nvidia | GHOST Day: AMLC 2022
GHOST Day: AMLC 2022 - Conference Opening
Просмотров 1912 года назад
GHOST Day: AMLC 2022 - Conference Opening
Challenges in developing Visual-Search system at Allegro, Bartosz Ludwiczuk &Bartosz Paszko @Allegro
Просмотров 1422 года назад
Challenges in developing Visual-Search system at Allegro, Bartosz Ludwiczuk &Bartosz Paszko @Allegro
Algorithmic Balancing Models for Multi-stakeholder Recommendations, Rishabh Mehrotra @ ShareChat
Просмотров 822 года назад
Algorithmic Balancing Models for Multi-stakeholder Recommendations, Rishabh Mehrotra @ ShareChat
Learning Representations for Hotel Ranking, Ioannis Partalas @ Expedia Group | GHOST Day: AMLC 2022
Просмотров 252 года назад
Learning Representations for Hotel Ranking, Ioannis Partalas @ Expedia Group | GHOST Day: AMLC 2022
Interactive ML in Healthcare AI, Rachel Wities @ Zebra Medical Vision | GHOST Day: AMLC 2022
Просмотров 532 года назад
Interactive ML in Healthcare AI, Rachel Wities @ Zebra Medical Vision | GHOST Day: AMLC 2022
Tweet-Topic Classification, Mateusz Fedoryszak @ Twitter | GHOST Day: AMLC 2022
Просмотров 1452 года назад
Tweet-Topic Classification, Mateusz Fedoryszak @ Twitter | GHOST Day: AMLC 2022
The structure of customer service data @Allegro, Aleksandra Chrabrowa | GHOST Day: AMLC 2022
Просмотров 1172 года назад
The structure of customer service data @Allegro, Aleksandra Chrabrowa | GHOST Day: AMLC 2022
Can we use graph generators when our real world graph data is limited?
wow, this is lacking in detail to provide a satisfactory explanation. too high level.
spr bro !!!!!!!!!!!!!!!
Can I download data of examples in this lecture?
Amazing introductory material to Pearlian causal analysis! Really complements the reading of Pearl's book and Molak's book on Causal Inference and Discovery in Python
promo sm
how to get the code for this please?
Interesting. Is there a Github repository for this project?
It's becoming clear that with all the brain and consciousness theories out there, the proof will be in the pudding. By this I mean, can any particular theory be used to create a human adult level conscious machine. My bet is on the late Gerald Edelman's Extended Theory of Neuronal Group Selection. The lead group in robotics based on this theory is the Neurorobotics Lab at UC at Irvine. Dr. Edelman distinguished between primary consciousness, which came first in evolution, and that humans share with other conscious animals, and higher order consciousness, which came to only humans with the acquisition of language. A machine with primary consciousness will probably have to come first. The thing I find special about the TNGS is the Darwin series of automata created at the Neurosciences Institute by Dr. Edelman and his colleagues in the 1990's and 2000's. These machines perform in the real world, not in a restricted simulated world, and display convincing physical behavior indicative of higher psychological functions necessary for consciousness, such as perceptual categorization, memory, and learning. They are based on realistic models of the parts of the biological brain that the theory claims subserve these functions. The extended TNGS allows for the emergence of consciousness based only on further evolutionary development of the brain areas responsible for these functions, in a parsimonious way. No other research I've encountered is anywhere near as convincing. I post because on almost every video and article about the brain and consciousness that I encounter, the attitude seems to be that we still know next to nothing about how the brain and consciousness work; that there's lots of data but no unifying theory. I believe the extended TNGS is that theory. My motivation is to keep that theory in front of the public. And obviously, I consider it the route to a truly conscious machine, primary and higher-order. My advice to people who want to create a conscious machine is to seriously ground themselves in the extended TNGS and the Darwin automata first, and proceed from there, by applying to Jeff Krichmar's lab at UC Irvine, possibly. Dr. Edelman's roadmap to a conscious machine is at arxiv.org/abs/2105.10461
hello pls can you help with this project .. thanks
hello bro can u help with me this project
How to get this ?I need it