Science Courses and Tutorials

In this post we will first discuss how to set up Spark to start easily performing analytics, either simply on your local machine or in a cluster on EC2. We then will explore Spark at an introductory level, moving towards an understanding of what Spark is and how it works (hopefully motivating further exploration). In the last two sections we will start to interact with Spark on the command line and then demo how to write a Spark application in Python and submit it to the cluster as a Spark job.

This is the first article of the "Big Data Processing with Apache Spark” series. In this first installment of Apache Spark article series, we'll look at what Spark is, how it compares with a typical MapReduce solution and how it provides a complete suite of tools for big data processing. Please see also: Part 2: Spark SQL, Part 3: Spark Streaming, Part 4: Spark Machine Learning, Part 5 Spark ML Data Pipelines, Part 6 Graph Data Analytics with Spark GraphX.

Learn how to use SQL to store, query, and manipulate data. SQL is a special-purpose programming language designed for managing data in a relational database, and is used by a huge number of apps and organizations. The tutorial covers SQL basics, more advanced SQL queries, relational queries in SQL, modifying databases with SQL, and pointers on what deeper topics to learn next.

This online course by Cybrary will take you from basic concepts to advanced scripts in just over 10 hours of material, with a focus on networking and security.

This repository provides tutorial code for deep learning researchers to learn PyTorch. In the tutorial, most of the models were implemented with less than 30 lines of code. Before starting this tutorial, it is recommended to finish Official Pytorch Tutorial.

This tutorial covers the skip gram neural network architecture for Word2Vec. My intention with this tutorial was to skip over the usual introductory and abstract insights about Word2Vec, and get into more of the details. Specifically here I’m diving into the skip gram neural network model.

Code reuse is a very common need. It saves you time for writing the same code multiple times, enables leveraging other smart people’s work to make new things happen. Even just for one project, it helps organize code in a modular way so you can maintain each part separately. When it comes to python, it means format your project so it can be easily packaged. This is a simple instruction on how to go from nothing to a package that you can proudly put it in your portfolio to be used by other people.

In November 2006, NVIDIA introduced CUDA®, a general purpose parallel computing platform and programming model that leverages the parallel compute engine in NVIDIA GPUs to solve many complex computational problems in a more efficient way than on a CPU.

The advent of multicore CPUs and manycore GPUs means that mainstream processor chips are now parallel systems. Furthermore, their parallelism continues to scale with Moore's law. The challenge is to develop application software that transparently scales its parallelism to leverage the increasing number of processor cores, much as 3D graphics applications transparently scale their parallelism to manycore GPUs with widely varying numbers of cores.

The CUDA parallel programming model is designed to overcome this challenge while maintaining a low learning curve for programmers familiar with standard programming languages such as C.

This guide is for C development for NVIDIA's CUDA programming platform.

The use of Graphics Processing Units for rendering is well known, but their power for general parallel computation has only recently been explored. Parallel algorithms running on GPUs can often achieve up to 100x speedup over similar CPU algorithms, with many existing applications for physics simulations, signal processing, financial modeling, neural networks, and countless other fields.

This course will cover programming techniques for the GPU. The course will introduce NVIDIA's parallel computing language, CUDA. Beyond covering the CUDA programming model and syntax, the course will also discuss GPU architecture, high performance computing on GPUs, parallel algorithms, CUDA libraries, and applications of GPU computing. Problem sets will cover performance optimization and specific GPU applications in numerical mathematics, medical imaging, finance, and other fields.

Labwork will require significant programming. A working knowledge of the C programming language will be necessary. Although CS 24 is not a prerequisite, it (or equivalent systems programming experience) is recommended.

If you are in the position I was where you are on the edge of building your own deep learning machine but a little unsure of time that you need to invest in getting that setup, this post is for you. And this is inspired by my fellow students, mainly Yad Faeq, Brendan Fortuner and our professor Jeremy Howard.

"Introduction to Databases" was one of Stanford's inaugural three massive open online courses in the fall of 2011 and was offered again in early 2013. January 2014 will mark its third offering. The course includes video lectures and demos with in-video quizzes to check understanding, in-depth standalone quizzes, a wide variety of automatically-checked interactive programming exercises, midterm and final exams, a discussion forum, optional additional exercises with solutions, and pointers to readings and resources. Taught by Professor Jennifer Widom, the curriculum draws from Stanford's popular Introduction to Databases course.

Seeing Theory is a project designed and created by Daniel Kunin with support from Brown University's Royce Fellowship Program and National Science Foundation group STATS4STEM. The goal of the project is to make statistics more accessible to a wider range of students through interactive visualizations.

Statistics, is quickly becoming the most important and multi-disciplinary field of mathematics. According to the American Statistical Association, statistician is one of the top ten fastest-growing occupations and statistics is one of the fastest-growing bachelor degrees. Statistical literacy is essential to our data driven society. Yet, for all the increased importance and demand for statistical competence, the pedagogical approaches in statistics have barely changed. Using Mike Bostock’s data visualization software, D3.js, Seeing Theory visualizes the fundamental concepts covered in an introductory college statistics or Advanced Placement statistics class. Students are encouraged to use Seeing Theory as an additional resource to their textbook, professor and peers.

A simple guide for getting started with git.

A readable explanation of generative adversarial networks (GANs) with example code using PyTorch.

Machine learning lecture notes, exercises, coding exercises, and more by Prof. Laurenz Wiskott of the Institut für Neuroinformatik at Ruhr-Universität Bochum, Germany. Topics include neural networks, Bayesian theory and graphical models, clustering and regression, optimization methods, support vector machines, reinforcement learning, and more.

Google Developers Codelabs provide a guided, tutorial, hands-on coding experience. Choose from over 100 tutorials. Most codelabs will step you through the process of building a small application, or adding a new feature to an existing application. They cover a wide range of topics such as Android Wear, Google Compute Engine, Project Tango, and Google APIs on iOS.

The other day, I was presented with a challenge: Describe how a neural network works without invoking the metaphor of the brain. The following is my attempt to meet that challenge. I will do this through the lens of a simplified self-driving car example.

This course offers an introduction to the finite sample analysis of high- dimensional statistical methods. The goal is to present various proof techniques for state-of-the-art methods in regression, matrix estimation and principal component analysis (PCA) as well as optimality guarantees. The course ends with research questions that are currently open. Taught by Prof. Philippe Rigollet.

Broadly speaking, Machine Learning refers to the automated identification of patterns in data. As such it has been a fertile ground for new statistical and algorithmic developments. The purpose of this course is to provide a mathematically rigorous introduction to these developments with emphasis on methods and their analysis. Taught by Prof. Philippe Rigollet.

Research into word embeddings is one of the most interesting in the deep learning world at the moment, even though they were introduced as early as 2003 by Bengio, et al. Most prominently among these new techniques has been a group of related algorithm commonly referred to as Word2Vec which came out of google research. In this post we are going to investigate the significance of Word2Vec for NLP research going forward and how it relates and compares to prior art in the field. In particular we are going to examine some desired properties of word embeddings and the shortcomings of other popular approaches centered around the concept of a Bag of Words (henceforth referred to simply as Bow) such as Latent Semantic Analysis.