Cluster analysis is a staple of unsupervised machine learning and data science. It is very useful for data mining and big data because it automatically finds patterns in the data, without the need for labels, unlike supervised machine learning. In a real-world environment, you can imagine that a robot or an artificial intelligence won't always have access to the optimal answer, or maybe there isn't an optimal correct answer. You'd want that robot to be able to explore the world on its own, and learn things just by looking for patterns. Do you ever wonder how we get the data that we use in our supervised machine learning algorithms?

What is a Time Series? Many data sets are cross-sectional and represent a single slice of time. However, we also have data collected over many periods - weekly sales data, for instance. This is an example of time series data. Time series analysis is a specialized branch of statistics used extensively in fields such as Econometrics and Operations Research.

In previous posts, I introduced Keras for building convolutional neural networks and performing word embedding. The next natural step is to talk about implementing recurrent neural networks in Keras. In a previous tutorial of mine, I gave a very comprehensive introduction to recurrent neural networks and long short term memory (LSTM) networks, implemented in TensorFlow. In this tutorial, I'll concentrate on creating LSTM networks in Keras, briefly giving a recap or overview of how LSTMs work. In this Keras LSTM tutorial, we'll implement a sequence-to-sequence text prediction model by utilizing a large text data set called the PTB corpus. All the code in this tutorial can be found on this site's Github repository. Recommended online course: If you are more of a video course learner, I'd recommend this inexpensive Udemy course to learn more about Keras and LSTM networks: Zero to Deep Learning with Python and Keras A LSTM network is a kind of recurrent neural network.

When it comes to AI adoption, the adage "the future is already here, it's just not evenly distributed" applies. There's not only a shortage of data scientists, but also a shortage of business stakeholders willing or accustomed to identifying problems capable of being solved with AI. That's the premise of a recent Harvard Business Review article by Kathryn Hume, "How to spot a machine learning opportunity, even if you aren't a data scientist." Hume makes the case that having an intuition for how machine learning algorithms work will be an important business skill in the foreseeable future. Fortunately, this skill can be learned.

During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still escapes current cognitive and linguistic theories. Recently, spectacular progress in the engineering science, notably, machine learning and wearable technology, offer the promise of revolutionizing the study of cognitive development. Machine learning offers powerful learning algorithms that can achieve human-like performance on many linguistic tasks. Wearable sensors can capture vast amounts of data, which enable the reconstruction of the sensory experience of infants in their natural environment. The project of 'reverse engineering' language development, i.e., of building an effective system that mimics infant's achievements appears therefore to be within reach. Here, we analyze the conditions under which such a project can contribute to our scientific understanding of early language development. We argue that instead of defining a sub-problem or simplifying the data, computational models should address the full complexity of the learning situation, and take as input the raw sensory signals available to infants. This implies that (1) accessible but privacy-preserving repositories of home data be setup and widely shared, and (2) models be evaluated at different linguistic levels through a benchmark of psycholinguist tests that can be passed by machines and humans alike, (3) linguistically and psychologically plausible learning architectures be scaled up to real data using probabilistic/optimization principles from machine learning. We discuss the feasibility of this approach and present preliminary results.

The Assassin's Creed series is known for its vast and richly detailed historical environments, and well... lots of murder. What you might not realize is just how much work goes into making these virtual windows into the past somewhat realistic. That's something Ubisoft is aiming to highlight with Assassin's Creed Origins' Discovery Tour. You can think of it as a museum-like experience set within the game's meticulous rendition of ancient Egypt. To turn one of the most popular gaming franchises in the world into a truly useful educational tool.

The future is looking good for machine learning. As data becomes cheaper and processing power gets even better, feats of data science become possible for everyone. However, hiring machine learning experts is something of an issue, as the demand continues to outstrip the supply. What's more, hiring a ML expert isn't cheap, as they regularly command some of the highest salaries in tech. Enter machine learning as a service (MLaaS).

Google, one of the world's largest tech companies, will focus on helping start-ups that integrate machine learning or artificial intelligence (AI) into their business strategy. This was disclosed to a room of journalists in San Francisco last week during Google Launchpad Accelerator. The programme brings together start-ups from emerging markets to participate in a two-week boot camp to take their business to the global stage. The start-ups need to already have a product, with a good market fit, and be ready to scale. During the intensive two weeks at Google's offices, start-ups are exposed to expert professionals and mentors in the technology and business space.

Support vector machines (SVM) and kernel methods are important machine learning techniques. In this short course, we will introduce their basic concepts. We then focus on the training and optimization procedures of SVM. Examples demonstrating the practical use of SVM will also be discussed. Basically we focus on classification.

Stochastic gradient descent (SGD) is an immensely popular approach for online learning in settings where data arrives in a stream or data sizes are very large. However, despite an ever-increasing volume of work on SGD, much less is known about the statistical inferential properties of SGD-based predictions. Taking a fully inferential viewpoint, this paper introduces a novel procedure termed HiGrad to conduct statistical inference for online learning, without incurring additional computational cost compared with SGD. The HiGrad procedure begins by performing SGD updates for a while and then splits the single thread into several threads, and this procedure hierarchically operates in this fashion along each thread. With predictions provided by multiple threads in place, a t-based confidence interval is constructed by decorrelating predictions using covariance structures given by the Ruppert--Polyak averaging scheme. Under certain regularity conditions, the HiGrad confidence interval is shown to attain asymptotically exact coverage probability. Finally, the performance of HiGrad is evaluated through extensive simulation studies and a real data example. An R package higrad has been developed to implement the method.