Archive for the ‘Numpy’ Category

Grokking Deep Learning

Wednesday, August 17th, 2016

Grokking Deep Learning by Andrew W. Trask.

From the description:

Artificial Intelligence is the most exciting technology of the century, and Deep Learning is, quite literally, the “brain” behind the world’s smartest Artificial Intelligence systems out there. Loosely based on neuron behavior inside of human brains, these systems are rapidly catching up with the intelligence of their human creators, defeating the world champion Go player, achieving superhuman performance on video games, driving cars, translating languages, and sometimes even helping law enforcement fight crime. Deep Learning is a revolution that is changing every industry across the globe.

Grokking Deep Learning is the perfect place to begin your deep learning journey. Rather than just learn the “black box” API of some library or framework, you will actually understand how to build these algorithms completely from scratch. You will understand how Deep Learning is able to learn at levels greater than humans. You will be able to understand the “brain” behind state-of-the-art Artificial Intelligence. Furthermore, unlike other courses that assume advanced knowledge of Calculus and leverage complex mathematical notation, if you’re a Python hacker who passed high-school algebra, you’re ready to go. And at the end, you’ll even build an A.I. that will learn to defeat you in a classic Atari game.

In the Manning Early Access Program (MEAP) with three (3) chapters presently available.

A much more plausible undertaking than DARPA’s quest for “Explainable AI” or “XAI.” (DARPA WANTS ARTIFICIAL INTELLIGENCE TO EXPLAIN ITSELF) DARPA reasons that:


Potential applications for defense are endless—autonomous aerial and undersea war-fighting or surveillance, among others—but humans won’t make full use of AI until they trust it won’t fail, according to the Defense Advanced Research Projects Agency. A new DARPA effort aims to nurture communication between machines and humans by investing in AI that can explain itself as it works.

If non-failure is the criteria for trust, U.S. troops should refuse to leave their barracks in view of the repeated failures of military strategy since the end of WWII.

DARPA should choose a less stringent criteria for trusting an AI. However, failing less often than the Joint Chiefs of Staff may be too low a bar to set.

NumPy / SciPy / Pandas Cheat Sheet

Thursday, June 11th, 2015

NumPy / SciPy / Pandas Cheat Sheet From quandl.

Useful but also an illustration of the tension between a true cheatsheet (one page, tiny print) and edging towards a legible but multi-page booklet.

I suspect the greatest benefit of a “cheatsheet” accrues to its author. The chores of selecting, typing and correcting being repetition that leads to memorization of the material.

I first saw this in a tweet by Kirk Borne.

The Matrix Cheatsheet

Tuesday, March 3rd, 2015

The Matrix Cheatsheet by Sebastian Raschka.

Sebastian has created a spreadsheet of thirty (30) matrix tasks and compares the code for each in: MATLAB/Octave, Python NumPy, R, and Julia.

Given the prevalence of matrices in so many data science tasks, this can’t help but be useful.

A bit longer treatment can be found at: The Matrix Cookbook.

I first saw this in a tweet by Yhat, Inc.

SunPy

Friday, February 14th, 2014

SunPy

From the webpage:

The SunPy project is a free and open-source software library for solar physics.

SunPy is a community-developed free and open-source software package for solar physics. SunPy is meant to be a free alternative to the SolarSoft data analysis environment which is based on the IDL scientific programming language sold by Exelis. Though SolarSoft is open-source IDL is not and can be prohibitively expensive.

The aim of the SunPy project is to provide the software tools necessary so that anyone can analyze solar data. SunPy is written using the Python programming language and is build upon the scientific Python environment which includes the core packages NumPy, SciPy. The development of SunPy is associated with that Astropy. SunPy was first created in 2011 by a small group of scientists and developers at the NASA Goddard Space Flight Center on nights and weekends.

Future employers will be interested in your data handling skills. Not whether you learned them as part of a hobby (astronomy), on your own or from a class. From a hobby just means you had fun learning them.

I first saw this in a tweet by Scientific Python.

100 numpy exercises

Thursday, January 30th, 2014

100 numpy exercises A joint effort of the numpy community.

The categories are:

Neophyte
Novice
Apprentice
Journeyman
Craftsman
Artisan
Adept
Expert
Master
Archmaster

Further on Numpy.

Enjoy!

I first saw this in a tweet by Gregory Piatetsky.