Data
The Pipe Operator : A Better Way To Nest Functions In R
During your data manipulation, exploration, and even analysis, functions can get complicated, putting one function inside of one another in order to accomplish tasks in one swoop. These are called nested functions. A nested function may look like something like this: Not only can this confuse you while you are coding, this looks quite ugly …
A Short Primer On Generalized Linear Models (GLM)
Generalized Linear Models (GLM) refers to a large class of models which include the familiar ordinary linear regression — ordinary least squares (OLS) regression — and the analysis of variance (ANOVA) models. A bag loaded with tricks (models, rather) Both OLS regression and ANOVA deal with continuous response variables. However, there are times that we …
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 …
TF Dev Summit ‘19 | Improving Text In Tensorflow
TF Dev Summit ‘19 | Improving Text In Tensorflow Learn how recent changes to Tensorflow make working with text data simpler and easier. Speaker: Mark Omernick
TF Dev Summit ‘19 | TensorFlow Federated (TFF): Machine Learning on Decentralized Data
TF Dev Summit ‘19 | TensorFlow Federated (TFF): Machine Learning on Decentralized Data TensorFlow Federated (TFF) is an open-source framework for machine learning and other computations on decentralized data. TFF has been developed to facilitate open research and experimentation with Federated Learning (FL), an approach to machine learning where a shared global model is trained …
TF Dev Summit ‘19 | Exascale Deep Learning for Climate Analytics
TF Dev Summit ‘19 | Exascale Deep Learning for Climate Analytics Climate change will have fundamental socio-economic impact and it is imperative for us to understand it better. This talk will show how TensorFlow was utilized on the world’s fastest supercomputer in order to extract pixel level segmentation masks of extreme weather phenomena in climate …
TF Dev Summit ’19 | TensorFlow Probability: Learning With Confidence
TF Dev Summit ’19 | TensorFlow Probability: Learning with confidence TensorFlow Probability (TFP) is a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware (TPU, GPU). It’s for data scientists, statisticians, and ML researchers/practitioners who want to encode domain knowledge to understand data and make …
How Artificial Intelligence Systems Could Threaten Democracy
U.S. technology giant Microsoft has teamed up with a Chinese military university to develop artificial intelligence systems that could potentially enhance government surveillance and censorship capabilities. Two U.S. senators publicly condemned the partnership, but what the National Defense Technology University of China wants from Microsoft isn’t the only concern. As my research shows, the advent …
How To Install Matplotlib
Overview This guide shows how to install Matplotlib, a Python 2D plotting library which produces publication-quality figures in a variety of hardcopy formats and interactive environments across platforms. Prerequisites Python has been installed Installation on Ubuntu Installation on Windows Optional but recommended. Setup a VirtualEnvironment and Pip has been installed. VirtualEnvironment for Ubuntu …
How Computers Help Biologists Crack Life’s Secrets
Once the three-billion-letter-long human genome was sequenced, we rushed into a new “omics” era of biological research. Scientists are now racing to sequence the genomes (all the genes) or proteomes (all the proteins) of various organisms – and in the process are compiling massive amounts of data. For instance, a scientist can use “omics” tools …