Neural Networks
Predicting How Well Neural Networks Will Scale
For all the progress researchers have made with machine learning in helping us doing things like crunch numbers, drive cars and detect cancer, we rarely think about how energy-intensive it is to maintain the massive data centers that make such work possible. Indeed, a 2017 study predicted that, by 2025, internet-connected devices would be using 20 …
TF Dev Summit ‘19 | Mesh-TensorFlow: Model Parallelism for Supercomputers
TF Dev Summit ‘19 | Mesh-TensorFlow: Model Parallelism for Supercomputers Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting suffers from problems including the inability to train very large models (due to memory constraints), high latency, and inefficiency …
Why Artificial Neural Networks Have A Long Way To Go Before They Can ‘See’ Like Us
Artificial neural networks were created to imitate processes in our brains, and in many respects – such as performing the quick, complex calculations necessary to win strategic games such as chess and Go – they’ve already surpassed us. But if you’ve ever clicked through a CAPTCHA test online to prove you’re human, you know that …
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 …
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 …
Google I/O 2019 | Teaching a Car to Drive Itself by Imitation and Imagination
Google I/O 2019 | Teaching a Car to Drive Itself by Imitation and Imagination Training a neural net to drive by pure observation requires ensuring that good behavior is being learned from the right signals and that test results in simulation can be transferred to the real world. This talk will walk you through the …