Stephen Downes

Knowledge, Learning, Community

Long post that introduces machine learning for designers. It requires a (free) O'Reilly login (sorry). People already expert in machine learning won't find anything new but I think it's worth the effort if you don't have background in the field.

"Conventional programming languages can be thought of as systems that are always correct about mundane things like concrete mathematical operations. Machine learning algorithms, on the other hand, can be thought of as systems that are often correct about more complicated things like identifying human faces in an image." There's a good set of recognition examples that illustrate this. It looks at biological models and deep learning, then discusses processing different types of inputs. Some of the tasks described include creating dialogue, feature discovery, designing, feedback loops, and more. It also looks at open source machine learning toolkits (TensorFlow, Torch, Caffe, cuDNN, Theano, Scikit-learn, Shogun, Spark MLlib, and Deeplearning4j) and machine Learning as a Service (MLaaS) platforms such as IBM Watson, Amazon Machine Learning, Google Prediction API, Microsoft Azure, BigML, and ClarifAI.

Today: 1058 Total: 1065 [Direct link] [Share]

Image from the website
View full size


Stephen Downes Stephen Downes, Casselman, Canada
stephen@downes.ca

Copyright 2024
Last Updated: Mar 29, 2024 02:19 a.m.

Canadian Flag Creative Commons License.

Force:yes