I built my first website with Dreamweaver, a WYSIWYG site builder that became popular during my teenage years. I was so proud of my creation. It was ugly, but I made it. Although my silly website didn’t take off as I had dreamed, it was a gateway drug to creating things on the internet. Dreamweaver and similar tools (FrontPage, Flash, etc.) dramatically reduced the barrier to creation especially for someone like myself at the time, a 15-year-old in high school with very basic understanding of HTML and CSS. Their impact on today’s tech ecosystem is understated and today we’re seeing a new wave of tools that are making creation more accessible and reinventing the way things are built for the internet.

We predict growth and adoption of Federated Learning, a new framework for Artificial Intelligence (AI) model development that is distributed over millions of mobile devices, provides highly personalized models and does not compromise the user privacy. The model development, training, and evaluation with no direct access to or labeling of raw user data. In markets such as India where hyper-personalisation and contextual recommendation will be key in driving app adoption or e-commerce purchases, the bet is that federated learning will play a key role in 2019. A new dawn for the AI world and a new hope!

For anyone who wants to be fluent in Machine Learning, understanding Shannon’s entropy is crucial. Shannon’s Entropy leads to a function which is the bread and butter of an ML practitioner?-?the cross entropy that is heavily used as a loss function in classification and also the KL divergence which is widely used in variational inference.

Artificial Intelligence and the technology behind it are growing at a furious pace. Marketers have realized its vast potential and are striving to extract the technology’s opportunities in full. There are numerous advancements being made in this regard, and many organizations have taken center stage of the AI world with in depth data analysis and data discovery solutions.

Excited about using AI to improve your organization’s operations? Curious about the promise of insights and predictions from computer models? I want to warn you about bias and how it can appear in those types of projects, share some illustrative examples, and translate the latest academic research on ‘algorithmic bias.’

In my last post I looked at generating synthetic data sets with the ‘synthpop’ package, some of the challenges and neat things the package can do. It is simple to use which is great when you have a single data set with independent features. This post will build on the last post by tackling other complications when attempting to synthesise data. These challenges occur regularly in practice and this post will offer a couple of solutions, but there are plenty more. If you haven’t read my previous post, check that out first and swing back here. I’ll detail how more complex synthesis can be done using synthpop.

As stated in the first article of this series, Classification is a subcategory of supervised learning where the goal is to predict the categorical class labels (discrete, unoredered values, group membership) of new instances based on past observations.

The art of forecasting stock prices has been a difficult task for many of the researchers and analysts. In fact, investors are highly interested in the research area of stock price prediction. For a good and successful investment, many investors are keen on knowing the future situation of the stock market. Good and effective prediction systems for stock market help traders, investors, and analyst by providing supportive information like the future direction of the stock market. In this work, we present a recurrent neural network (RNN) and Long Short-Term Memory (LSTM) approach to predict stock market indices.

A convolutional neural network is a type of Deep neural network which has got great success in image classification problems, it is primarily used in object recognition by taking images as input and then classifying them in a certain category. The major advantage of CNN is that it learns the filters that in traditional algorithms were hand-engineered, so it takes less human effort.

So much is going on with Stan that it can be hard to keep track, so we (the Stan project) are starting a monthly update and newsletter. If you want to be included in the monthly mailing list, just type in your email here.

The Internet has revolutionised how we interact with each other, how we build businesses, and even how we lead our daily life. It has allowed humans to evolve from doing the manual labour work to the intelligent species which writes software to get things done. Today, we are about to witness a whole new revolution, where we do not program the machine with specific instructions, but rather, we feed it with data, so that the machine itself will write the code.

LSA itself is an unsupervised way of uncovering synonyms in a collection of documents.To start, we take a look how Latent Semantic Analysis is used in Natural Language Processing to analyze relationships between a set of documents and the terms that they contain. Then we go steps further to analyze and classify sentiment. We will review Chi Squared for feature selection along the way. We will use Recurrent Neural Networks, and in particular LSTMs, to perform sentiment analysis in Keras. Let’s get started!