PyData Session List
10 Years of Automated Category Classification for Product Data
Johannes Knopp
Artificial Intelligence, Deep Learning, Data Science, Infrastructure, Machine Learning, Data Engineering10 years ago we built a classifier for categorizing product data. Let's take a journey through the lessons we learned over the years about building, maintaining, and modernizing the category classifier.
A Bayesian Workflow with PyMC and ArviZ
Corrie Bartelheimer
Data Science, StatisticsAn Example of a Bayesian Workflow using PyMC and ArviZ: Predicting House Prices in Berlin
A Tour of JupyterLab Extensions
Jeremy Tuloup
Community, Data Science, IDEs/ Jupyter, VisualisationA tour of 20 JupyterLab extensions, in 20 minutes. Demos included!
Active Learning with Bayesian Nonnegative Matrix Factorization for Recommender Systems
Gönül Aycı
StatisticsAn approach for a matrix completion problem using the Bayesian Nonnegative Matrix Factorization (NMF).
AI Intentions and Code Completion
Vasily Korf
Artificial Intelligence, Code-Review, IDEs/ Jupyter, PythonDatalore supports intentions – code suggestions based on what you’ve just written.
Airflow: your ally for automating machine learning and data pipelines
Enrica Pasqua, Bahadir Uyarer
Big Data, Infrastructure, Machine Learning, Data EngineeringAutomate your machine learning and data pipelines with Apache Airflow
Algo.Rules - How do we get the ethics into the code?
Carla Hustedt
AlgorithmsAlgo.Rules - How do we get the ethics into the code? 9 rules for the design of algorithmic systems
Applying deployment oriented mindset for building Machine Learning models
Marianna Diachuk
Data Science, Machine LearningGetting stuck for months trying to deploy the model and fighting with data inconsistency and bugs? This talk will introduce the way to build the development process with deployment in mind.
Are you sure about that?! Uncertainty Quantification in AI
Florian Wilhelm
Artificial Intelligence, Deep Learning, Data Science, Machine Learning, ScienceAre you sure about that?! Uncertainty Quantification in AI helps you to decide if you can trust a prediction or rather not.
Automated Feature Engineering and Selection in Python
Franziska Horn
Data Science, Machine Learning, Science, Data Engineering, StatisticsAutomated feature engineering and selection in Python with the autofeat library.
Automating feature engineering for supervised learning? Methods, open-source tools and prospects.
Thorben Jensen
Artificial Intelligence, Algorithms, Data Science, Machine Learning, Data EngineeringHow to automate the labor-intensive task of feature engineering for Machine Learning? This talk gives an overview on methods, presents open-source libraries for Python, and compares their performance.
Avoiding ML FOBO
Rachel Berryman, Dânia Meira
Algorithms, Business & Start-Ups, Data Science, Machine LearningIs FOBO (Fear Of Better Option) preventing you from delivering practical ML products? Join 'Avoiding ML FOBO' to learn tips for cutting through the hype.
Birds of a feather flock together - Tracking pigeons with Python and OpenCV
Neslihan Edes
Computer Vision, IDEs/ Jupyter, ScienceIn this talk I want to demonstrate how to leverage existing Open Source technologies to implement basic movement tracking use cases.
Build a Machine Learning pipeline with Jupyter and Azure
Daniel Heinze
Computer Vision, Deep Learning, DevOps, IDEs/ Jupyter, Machine Learning, APIs, PythonBuild a Machine Learning pipeline with Jupyter and Azure: https://notebooks.azure.com/Starlord/projects/pycon-ml-jupyter-azure
CANCELED: Create CUDA kernels from Python using Numba and CuPy.
Valentin Haenel
Algorithms, Big Data, Data Science, Parallel ProgrammingLearn to program GPUs (e.g. Kernels) in Python with CuPy and Numba.
CANCELLED: First steps in Julia
Felicia Burtscher
Artificial Intelligence, Algorithms, Deep Learning, Data Science, Networks, Machine Learning, Science#julia_introduction. why julia is better than python. machine learning made eady with juliabox.
Creating an Interactive ML Conference Showcase
Harald Bosch
Artificial Intelligence, Computer Vision, Deep Learning, IDEs/ Jupyter, Machine LearningBuild a ML showcase using #transferlearning, #keras, #WebRTC, #python
Current affairs, updates, and the roadmap of scikit-learn and scikit-learn-contrib
Adrin Jalali
Artificial Intelligence, Community, Code-Review, Machine Learningan update on recent scikit-learn changes, current affairs, and the roadmap
Dash: Interactive Data Visualization Web Apps with no Javascript
Dom Weldon
Data Science, Visualisation, WebInteractive webpages with no JS? What could possibly go wrong?
Data Literacy for Managers
Alexander CS Hendorf
Artificial Intelligence, Business & Start-Ups, Data Science, Machine Learning, Use CasesArtificial Intelligence need to be better understood in enterprises. Close the communications gap between engineers and management. Making data litteracy happen in your organisation.
Decentralized and Privacy-Preserving ML via TensorFlow Federated
Peter Kairouz, Amlan Chakraborty
Artificial Intelligence, Deep Learning, Data Science, Machine Learning, Data EngineeringMeet TensorFlow Federated: an open-source framework for machine learning and other computations on decentralized data.
Deep Learning for Healthcare with PyTorch
Valerio Maggio
Artificial Intelligence, Deep Learning, Machine Learning, ScienceThis tutorial provides a general introduction to the PyTorch Deep Learning framework with specific focus on Deep Learning applications for Precision Medicine and Computational Biology.
Detecting and Analyzing Solar Panels in Switzerland using Aerial Imagery
Martin Christen
Big Data, Computer Vision, Deep Learning, Data Science, Machine Learning, VisualisationDetecting Solar Panels from aerial imagery using #Python #DeepLearning #CrowdSourcing
Does hate sound the same in all languages?
Andrada Pumnea
Deep Learning, Data Science, Natural Language Processing, Data Mining / ScrapingDoes hate sound the same in all languages? Join this talk to learn more about hate speech detection in a language less circulated, from dataset creation to hate speech recognition model..
Embrace uncertainty! Why to go beyond point estimators for valuable ML applications
Stefan Maier
Algorithms, Data Science, Machine Learning, StatisticsUsually, uncertainties of Machine Learning predictions are just regarded as a sign of poor prediction accuracy or as a consequence of lacking input features. This talk illustrates how modeling uncertainties can improve ML based decisions.
Equivariance in CNNs: how generalising the weight-sharing property increases data-efficiency
Marysia Winkels
Artificial Intelligence, Algorithms, Computer Vision, Deep Learning, Data Science, Machine Learning, ScienceEquivariance in CNNs: how generalising the weight-sharing property increases data-efficiency
Extended Ligthning Talks CANCELLED: Crunching Numbers Like a Journalist
Marie-Louise Timcke
Big Data, Data Science, StatisticsMarie will talk about how newsrooms work with data on a day to day basis, and how scientific accuracy fits in with the pace of news reporting.
Fairness in decision-making with AI: a practical guide & hands-on tutorial using Aequitas
Pedro Saleiro
Data Science, Machine Learning, Use CasesIn this tutorial, we are going to deep dive into algorithmic fairness, from metrics and definitions to practical case studies, including bias audits using Aequitas (http://github.com/dssg/aequitas) in real policy problems where AI is being used
Fighting fraud: finding duplicates at scale
Alexey Grigorev
Data Science, Infrastructure, Machine Learning, Data EngineeringFight fraudsters at scale: use machine learning to find duplicates in 10 million ads daily
Friend or Foe: Comparison of R & Python in Data Wrangling & Visualisation
Yuta Kanzawa
Data Science, Machine Learning, Visualisation, StatisticsR and Python are different in community and as language. Still, comparing them in their common fields such as data wrangling and visualisation, useRs and Pythonistas will deepen mutual understanding.
Gaussian Process for Time Series Analysis
Dr. Juan Orduz
Algorithms, Data Science, Machine Learning, StatisticsGaussian process for regressions problems and time series forecasting
Gaussian Progress
Vincent Warmerdam
Artificial Intelligence, Algorithms, Data Science, IDEs/ Jupyter, Machine Learning, Statisticsgaussian progress. it's meta, but also the most normal conference title this year!
Get to grips with pandas and scikit-learn
Sandrine Pataut
Algorithms, Data Science, Machine LearningGet to grips with pandas and scikit-learn: a first contact with data science using python
Hidden Markov Models for Chord Recognition - Intuition and Applications
Caio Miyashiro
Algorithms, Data Science, Machine Learning, StatisticsCome check out Caio's workshop on music+programming+stats on PyData
Hide Code, Minimize Dependencies, Boost Performance - The PyTorch JIT
Tilman Krokotsch
Artificial Intelligence, Deep Learning, Data Science, Machine LearningPyTorch makes developing, training and debugging deep neural networks convenient. Learn how to export your trained model using its just-in-time (JIT) compiler to hide your network architecture, minimize code dependencies and use it in the C++ API. It's getting faster, too!
How strong is my opponent? Using Bayesian methods for skill assessment
Darina Goldin
AlgorithmsIntroduction to the ranking algorithms Elo, Glicko2, and Trueskill.
How to choose better colors for your data visualizations
Daniel Ringler
Data Science, VisualisationYou want to choose better colors for all the charts that you create with Python but you do not know where to start? This talk will teach you some basics about color theory so your charts will show what is important (and look beautiful).
How to write tests that need a lot of data?
Sander Kooijmans
Algorithms, Code-ReviewIn this talk Sander explains how to write tests that need a lot of data using code of a warehouse management system as example.
Interpretable Machine Learning: How to make black box models explainable
Alexander Engelhardt
Data Science, Machine LearningIn this talk, we'll find out how to interpret the predictions of otherwise black-box models.
Julia for Python
Simon Danisch
Data Science, Infrastructure, IDEs/ Jupyter, Parallel ProgrammingJulia is a new Language, that is fast, high level, dynamic and optimized for Data Science. Learn about Julia's strengths and how you can integrate it in your Python workflow!
Kartothek – Table management for cloud object stores powered by Apache Arrow and Dask
Florian Jetter
Big Data, Data EngineeringKartothek - Table management for cloud object stores powered by @ApacheArrow and @dask_dev
Law, ethics and machine learning – a curious ménage à trois
Dr. Benjamin Werthmann
Artificial Intelligence, Big Data, Machine LearningFind out and discuss how law and ethics should be included in a framework for machine learning that protects creativity and effectiveness
Lessons Learned as a Product Manager in Data Science
Tereza Iofciu
Business & Start-Ups, Data Science, Machine LearningHow many languages does the data science product manager need to speak?
Leveraging ML to obtain fine-grained (yet reliable) causal estimates from A/B tests and experiments
Maximilian Eber
Data Science, Machine Learning, Science, StatisticsHow to use machine learning to evaluate randomised experiments and A/B tests
Leveraging the advantages of Bayesian Methods to build a data science product using PyMC3
Korbinian Kuusisto
Algorithms, Business & Start-Ups, Data Science, Machine Learning, Science, StatisticsHow can one leverage the power of Bayesian methods to build a successful data science product?
Loss Function Theory 101
David Wölfle
Artificial Intelligence, Algorithms, Deep Learning, Data Science, Machine Learning, StatisticsThis talk covers the theoretical background behind two common loss functions, mean squared error and cross entropy, including why they are used for machine learning at all, and what limitations you should keep in mind.
Machine learning with little data - from digital twin to predictive maintenance
Andreas Hantsch
Deep Learning, Machine Learning, ScienceThis talk is about the coupling of a digital twin model and a machine learning predictive maintenance algorithm in order to be able to detect anomalies in the operation of a not well-known hardware system.
Making the complex simple in data viz
Tania Vasilikioti
Data Science, VisualisationCreating graphics that convey the desired message, are easily interpretable, but also beautiful can be a daunting task. Come to this talk to learn how to use The Grammar of Graphics to make any complex graphic simple, in Python.
Managing the end-to-end machine learning lifecycle with MLFlow
Tobias Sterbak
Data Science, Infrastructure, Machine Learning, Data EngineeringHow to manage the end-to-end machine learning lifecycle with MLflow.
Panel: Turn any notebook into a deployable dashboard
Philipp Rudiger
Data Science, IDEs/ Jupyter, VisualisationIntroducing Panel: Turn any notebook into a deployable dashboard
Practical DevOps for the busy data scientist
Dr. Tania Allard
Algorithms, Big Data, Data Science, DevOps, Machine LearningDevops for the busy data scientist: learn how to leverage these practices to improve your workflows
Privacy-preserving Machine Learning for text processing
Sarah Diot-Girard
Artificial Intelligence, Data Science, Natural Language Processing, Machine LearningData privacy can be tricky when doing Natural Language Processing, join us to explore the different strategies you can use to keep your user data safer!
Production-level data pipelines that make everyone happy using Kedro
Yetunde Dada
Data Science, DevOps, Machine Learning, Data EngineeringLearn how easy it is to apply software engineering principles to your data science and data engineering code. Expect an overview of Kedro, a library that implements best practices for data pipelines with an eye towards productionizing ML models.
Professional Development and Career Progression for Data Scientists
Noa Tamir
Business & Start-Ups, Community, Data ScienceHow to level up your skills and develop your your career by making the most of on the job opportunities, as well as open source contributions
Python-Powered OSINT! Modernising Open Source Intelligence for Investigating Disinformation
Chiin-Rui Tan, Dare Imam-Lawal
Artificial Intelligence, Algorithms, Data Science, Machine Learning, Web, Data Mining / Scraping, Use CasesSocio-Technical Python for OSINT! The old state discipline of gathering intelligence from open sources is today critical for investigating Disinformation but has lacked modernisation. A former UK Gov Head of DataSci presents a maturity model for updating legacy OSINT with Python!
Quantum computing with Python
James Wootton
Algorithms, Infrastructure, Microcontrollers, Science, APIsEvery Python user can play with one of the world's most advanced technologies: quantum computers. This session will tell you how you can and why you should.
Rethinking Open Source in the Era of Cloud & Machine Learning
Peter Wang
PythonOpen Source is a wildly successful and crucial part of many areas of modern technology. However, the ’sustainability crisis’ and the age of cloud computing have threatened its core mechanisms.
Should I stay or should I go? Optimal exercise decisions using the Longstaff-Schwartz algorithm
Benedikt Rudolph
Algorithms, Business & Start-Ups, Data Science, Science, StatisticsLearn about a simple least-squares approach to evaluate financial exercise options and make optimal exercise decisions.
skorch: A scikit-learn compatible neural network library that wraps pytorch
Benjamin Bossan
Deep Learning, Data Science, Machine LearningCombine the best of sklearn and PyTorch by using skorch. This talk shows you why and how to use skorch and what cool features it has to offer.
Tackle the problems that really matter - leverage the power of data science in the service of humanity
Eva Schreyer, Lisa Zäuner
Business & Start-Ups, Community, Data ScienceWe talk about how DSSG @dssgber brings together data scientist volunteers and non-profit organisations to tackle their data challenges in various events.
Take control of your hearing: Accessible methods to build a smart noise filter
Peggy Sylopp, Aislyn Rose
Artificial Intelligence, Algorithms, Computer Vision, Deep Learning, Data Science, Machine Learning, ScienceControl what you hear with deep learning and open audio databases. The developer and manager of \\NoIze//, a project supported by Prototype Fund, share what’s helped them build an open source smart, low-computational noise filter in Python.
The Sound of Silence: Online Misogyny and How we Model it
Teresa Ingram
Community, Natural Language Processing, Machine LearningOpt Out of Online Sexism - From a Problem to Open Source Activism and the Mechanics of Change
Time Series Anomaly Detection for Bottling Machine Maintenance
Andrea Spichtinger
Algorithms, Data Science, Machine LearningAnomaly detection in time series data from mechanical motors in bottling machines, set productive on an AWS edge device. #AnomalyDetection #UnsupervisedML #AWS
Time series modelling with probabilistic programming
Sean Matthews, Jannes Quer
Data Science, StatisticsProbabilistic time-series forecasting @ Deloitte Analytics Institute
Tools that help you get your experiments under control
Katharina Rasch
Artificial Intelligence, Data Science, DevOps, InfrastructureThere is now a wealth of tools that support data science best practices (e.g. tracking experiments, versioning data). Let’s take a look at which tools are available and which ones might be right for your project.
Transforming a Legacy System into a Bias-Mitigating AI Solution for Debt Repayment
Avaré Stewart
Artificial Intelligence, Data Science, Natural Language Processing, Machine Learning, Data EngineeringUnleash Intelligence in you Data Transform a Legacy System into Bias-Mitigating AI Solution for Debt Repayment with Tesseract, SpaCy, & AI Fairness 360
Using adversarial samples to break and robustify your Vision Neural Network Models
Irina Vidal Migallón
Artificial Intelligence, Computer Vision, Deep Learning, Machine LearningHow much time & risk do you have? Ways to robustify your vision NN model before you let it go live.
Using machine learning for Level Generation in Snake (video-game)
Filipe Silva
Data Science, Machine LearningUsing machine learning models for level generation in video-games
Using Overhead Video Capture to Analyse Grouping Behaviour of Dancers in a Silent Disco
Nelson Mooren
Computer Vision, ScienceI built upon Python's OpenCV library to detect locations of dancers in a silent disco, using their headphone lights as a proxy, and performed network analysis to investigate their grouping behaviour based on the playlists people were listening to.
Version Control for Data Science
Alessia Marcolini
Artificial Intelligence, Data Science, Machine LearningVersioning in Data Science projects can be pretty painful: are you able to track the data sets along with the code itself and some of the resulting models?
Visualizing Interactive Graph Networks in Python
Jan-Benedikt Jagusch
Data Science, IDEs/ Jupyter, Networks, Visualisation, PythonJoin @jan_jagusch's talk to learn about visualizing interactive network graphs in Python.
vtext: text processing in Rust with Python bindings
Roman Yurchak
Natural Language Processingvtext: text processing in Rust with Python bidings #pyconde #pydataberlin
Want to have a positive social impact as a data scientist?
Ellen König
Community, Data ScienceFind your individual approach towards more positive social impact by conducting experiments! I'll show you how.
Where Linguistics meets Natural Language Processing
Mariana Capinel
Natural Language ProcessingThis talk explains how linguistics describes language - via phonetics-phonology, morphology, syntax, semantics and pragmatics. We will combine linguistic concepts with models through examples for NLP newbies.
Why you don’t see many real-world applications of Reinforcement Learning.
Yurii Tolochko
Artificial Intelligence, Algorithms, Deep Learning, Machine Learning, StatisticsWhy doesn’t RL show the same success as (un)supervised learning? Inherent difficulties facing RL and avenues for future work
Why you should (not) train your own BERT model for different languages or domains
Marianne Stecklina
Artificial Intelligence, Deep Learning, Data Science, Natural Language Processing, Machine Learning, ScienceLanguage models like BERT can capture general language knowledge and transfer it to new data and tasks. However, applying a pre-trained BERT to non-English text has limitations. Is training from scratch a good (and feasible) way to overcome them?
Your Name Is Invalid!
Miroslav Šedivý
Algorithms, Community, Natural Language Processing, Web, Data Mining / Scraping, Use CasesIf your code tells me “Your Name Is Invalid!”, then your code is probably invalid. Names of people cannot be invalid.
Filter