With commentators arguing about how artificial intelligence is reshaping the world, lots of people want to get up to speed on what AI might mean for them. There are many great articles, videos, courses and games online to help you learn about AI: but knowing where to start can be difficult. To answer that question, our researcher Laura Caccia has put together a week-long crash course to get you up to speed with the basic developments and debates shaping the field of artificial intelligence: how it works, why it's important, and what it can do for you. We've recommended two books that cost a total of £20, and the rest of the materials are all available for free online.

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by applying it to stochastic gradient descent, stochastic gradient descent with Nesterov momentum, and Adam, showing that it significantly reduces the need for the manual tuning of the initial learning rate for these commonly used algorithms. Our method works by dynamically updating the learning rate during optimization using the gradient with respect to the learning rate of the update rule itself. Computing this "hypergradient" needs little additional computation, requires only one extra copy of the original gradient to be stored in memory, and relies upon nothing more than what is provided by reverse-mode automatic differentiation.

This is a guest post by Adrian Rosebrock. Adrian is the author of PyImageSearch.com, a blog about computer vision and deep learning. Adrian recently finished authoring Deep Learning for Computer Vision with Python, a new book on deep learning for computer vision and image recognition using Keras. In this tutorial, we will present a simple method to take a Keras model and deploy it as a REST API. The examples covered in this post will serve as a template/starting point for building your own deep learning APIs -- you will be able to extend the code and customize it based on how scalable and robust your API endpoint needs to be.

Arrays are the main data structure used in machine learning. In Python, arrays from the NumPy library, called N-dimensional arrays or the ndarray, are used as the primary data structure for representing data. In this tutorial, you will discover the N-dimensional array in NumPy for representing numerical and manipulating data in Python. A Gentle Introduction to N-Dimensional Arrays in Python with NumPy Photo by patrickkavanagh, some rights reserved. Take my free 7-day email crash course now (with sample code).

Sparse dictionary learning (SDL) has become a popular method for adaptively identifying parsimonious representations of a dataset, a fundamental problem in machine learning and signal processing. While most work on SDL assumes a training dataset of independent and identically distributed samples, a variant known as convolutional sparse dictionary learning (CSDL) relaxes this assumption, allowing more general sequential data sources, such as time series or other dependent data. Although recent work has explored the statistical properties of classical SDL, the statistical properties of CSDL remain unstudied. This paper begins to study this by identifying the minimax convergence rate of CSDL in terms of reconstruction risk, by both upper bounding the risk of an established CSDL estimator and proving a matching information-theoretic lower bound. Our results indicate that consistency in reconstruction risk is possible precisely in the `ultra-sparse' setting, in which the sparsity (i.e., the number of feature occurrences) is in $o(N)$ in terms of the length N of the training sequence. Notably, our results make very weak assumptions, allowing arbitrary dictionaries and dependent measurement noise. Finally, we verify our theoretical results with numerical experiments on synthetic data.

In a future teeming with robots and artificial intelligence, humans seem to be on the verge of being crowded out. But in reality the opposite is true. To be successful, organizations need to become more human than ever. Organizations that focus only on automation will automate away their competitive edge. The most successful will focus instead on skills that set them apart and that can't be duplicated by AI or machine learning.

The Python numerical computation library called NumPy provides many linear algebra functions that may be useful as a machine learning practitioner. In this tutorial, you will discover the key functions for working with vectors and matrices that you may find useful as a machine learning practitioner. This is a cheat sheet and all examples are short and assume you are familiar with the operation being performed. You may want to bookmark this page for future reference. Linear Algebra Cheat Sheet for Machine Learning Photo by Christoph Landers, some rights reserved.

About this course: What is machine learning, and what kinds of problems can it solve? Google thinks about machine learning slightly differently -- of being about logic, rather than just data. We talk about why such a framing is useful when thinking about building a pipeline of machine learning models. Then, we discuss the five phases of converting a candidate use case to be driven by machine learning, and consider why it is important the phases not be skipped. We end with a recognition of the biases that machine learning can amplify and how to recognize this.

A school in China has started a new course to teach its students how to play video games as a future profession. The school hopes the £1,470-per-year'eSports and Management' course could help ambitious teenagers cash in on China's £116 million digital gaming industry. During the first year of the course, the students in their teens and early 20s spend 50 per cent of their time gaming and the rest on study'theory lessons' to ensure they would succeed in the industry. Teenagers majoring in'eSports and Management' listen to teacher Yang Xiao explain game techniques at the school The Lanxiang Technical School, situated in the city of Jinan in eastern China, launched its eSports course last September and has attracted 50 students in its inaugural year. 'At first, many parents thought it was just about playing video games,' school director Rong Lanxiang, told AFP. 'In fact, it's not the case, eSport is developing to a very high degree and it's become an economic growth driver.'

SYSTRAN and HarvardNLP are very pleased to hold the first OpenNMT Workshop in Paris on March 2nd at Station F, followed by the first ever OpenNMT Hackathon on March 3rd at Télécom ParisTech. OpenNMT is an Open Source project providing neural technologies for different tasks such as automatic machine translation, text generation and summarization. The OpenNMT project is a collection of implementations on multiple frameworks designed to be simple to use and easy to extend, while maintaining efficiency and state-of-the-art accuracy. Registration is FREE and OPEN to both the OpenNMT community as well as anyone interested in Deep Learning applications for natural language processing. During the daylong hackathon, we will provide hands-on training, but also development sessions to share good development practices and to kick off development of new features or interfaces.