PyCon 2019 | Put Down The Deep Learning: When Not To Use Neural Networks And What To Do Instead
PyCon 2019 | Put Down The Deep Learning: When Not To Use Neural Networks And What To Do Instead Speaker: Rachael Tatman The deep learning hype is real, and the Python ecosystem makes it easier than ever to neural networks to everything from speech recognition to generating memes. But when picking a model architecture …
PyCon 2019 | Everything at Once: Python’s Many Concurrency Models
PyCon 2019 | Everything at Once: Python’s Many Concurrency Models Speaker: Jess Shapiro Python makes it incredibly easy to build programs that do what you want. But what happens when you want to do what you want, but with more input? One of the easiest things to do is to make a program concurrent …
PyCon 2019 | Machine Learning Model And Dataset Versioning Practices
PyCon 2019 | Machine learning model and dataset versioning practices Speaker: Dmitry Petrov Python is a prevalent programming language in machine learning (ML) community. A lot of Python engineers and data scientists feel the lack of engineering practices like versioning large datasets and ML models, and the lack of reproducibility. This lack is particularly …
PyCon 2019 | Modern Solvers: Problems Well-Defined Are Problems Solved
PyCon 2019 | Modern solvers: Problems well-defined are problems solved Speaker: Raymond Hettinger Every programmer should learn to use solvers, tools that reason directly from a description of a problem to its solution. Tools like AlphaZero can formulate winning strategies for games given only a description of the rules of the game. For certain …
Google I/O 2019 | TensorFlow Extended: Machine Learning Pipelines and Model Understanding
Google I/O 2019 | TensorFlow Extended: Machine Learning Pipelines and Model Understanding This talk will focus on creating a production machine learning pipeline using TFX. Using TFX developers can implement machine learning pipelines capable of processing large datasets for both modeling and inference. In addition to data wrangling and feature engineering over large datasets, TFX …
Google I/O 2019 | Getting Started with TensorFlow 2.0
Google I/O 2019 | Getting Started with TensorFlow 2.0 TensorFlow 2.0 is here! Understand new user-friendly APIs for beginners and experts through code examples to help you create different flavors of neural networks (Dense, Convolutional, and Recurrent) and understand when to use the Keras Sequential, Functional, and Subclassing APIs for your projects. Speakers: Josh …
The Information Arms Race Can’t Be Won, But We Have To Keep Fighting
Arms races happen when two sides of a conflict escalate in a series of ever-changing moves intended to outwit the opponent. In biology, a classic example comes from cheetahs and gazelles. Over time, these species have evolved for speed, each responding to the other’s adaptations. A host of weirder examples come from the biology of …
Google Cloud Next 2019 | BigQuery Tips: Nested and Repeated Fields And How GOJEK Builds Data Warehouses
Google Cloud Next 2019 | Retail Sessions Google Cloud Next 2019 | BigQuery Tips: Nested and Repeated Fields And How GOJEK Builds Data Warehouses Gain expert advice on BigQuery to take advantage of data warehousing. In this session, GOJEK, a global company with multiple products and services and lots of data, will share how they …
Google Cloud Next 2019 | Everyone Flies Faster When BigQuery Fuels The BI Engines At AirAsia
Google Cloud Next 2019 | Retail Sessions Google Cloud Next 2019 | Everyone Flies Faster When BigQuery Fuels The BI Engines At AirAsia Building real-time analytics dashboards with sub-second query latency can be fraught with complexity or high cost. But, does it have to be? In this session we’ll unpack how AirAsia, South East Asia’s …
To Stop The Machines Taking Over We Need To Think About Fuzzy Logic
Amid all the dire warnings that machines run by artificial intelligence (AI) will one day take over from humans we need to think more about how we program them in the first place. The technology may be too far off to seriously entertain these worries – for now – but much of the distrust surrounding …