Domino Data Lab

JUNE 8, 2021

The intuition here is that a decision boundary that leaves a wider margin between the classes generalises better, which leads us to the key property of support vector machines — they construct a hyperplane in a such a way that the margin of separation between the two classes is maximised (Haykin, 2009). Derivation of a Linear SVM. Fisher, R.

Optimization 76

Optimization Machine Learning Measurement Data Science 76

Perceptual Edge

FEBRUARY 22, 2021

On April 15, 2021, my book Now You See It (2009) will become available in its second edition with the revised subtitle An Introduction to Visual Data Sensemaking. Now You See It: An Introduction to Visual Data Sensemaking. Now You See It teaches the concepts, principles, and practices of visual data sensemaking.

IT 84

IT Statistics Visualization Interactive 84

Domino Data Lab

MAY 8, 2019

On the other hand, as Lipton emphasized, while the tooling produces interesting visualizations, visualizations do not imply interpretation. ML model interpretability and data visualization. From my experiences leading data teams, when a business is facing difficult challenges, data visualizations can help or hurt.

Machine Learning 105

Machine Learning Data Science Modeling Visualization 105

The Unofficial Google Data Science Blog

NOVEMBER 17, 2020

On the one hand, basic statistical models (e.g. TF Lattice offers semantic regularizers that can be applied to models of varying complexity, from simple Generalized Additive Models, to flexible fully interacting models called lattices, to deep models that mix in arbitrary TF and Keras layers. monotonicity, diminishing returns).

Machine Learning 108

Machine Learning Deep Learning Modeling Interactive 108

Domino Data Lab

JULY 9, 2019

When he retired in 2009 he had some time on his hands. Here is a picture of The New York Times on its birthday in 1851, and for the vast majority of its lifespan this is pretty much what the user experience of interacting with The New York Times looks like. For visualization we’re not building our own dashboards.

Data Science 112

Data Science Machine Learning Advertising Modeling 112