By end of this article, you will see what Apple CoreML is and why it is gaining the momentum. We will also look into implementation details of CoreML by building a message spam classification app for iPhone. We will finish off the article by objectively looking at pros and cons of the same.
In Part 1 of this series, we got started by looking at the ts object in R and how it represents time series data. In Part 2, I’ll discuss some of the many time series transformation functions that are available in R. This is by no means an exhaustive catalog. If you feel I left out anything important, please let me know. I compile these posts as a guide in RMarkdown which I plan to make available on the web soon.
Imitation learning, a.k.a behavioral cloning, is learning from demonstration. In other words, in imitation learning, a machine learns how to behave by looking at what a teacher (or expert) does and then mimics that behavior. An example can be when we collect driving data from human and then use that data for a self driving car.
This is a multi-part series of tutorials, in which we develop the mathematical and algorithmic underpinnings of deep neural networks from scratch and implement our own neural network library in Python, mimicing the TensorFlow API.
In many real-world classification problems, we stumble upon training data with unbalanced classes. This means that the individual classes do not contain the same number of elements. For example, if we want to build an image-based skin cancer detection system using convolutional neural networks, we might encounter a dataset with about 95% negatives and 5% positives. This is for good reasons: Images associated with a negative diagnosis are way more common than images with a positive diagnosis. Rather than regarding this as a flaw in the dataset, we should leverage the additional information that we get. This blog post will show you how.
This blog continues on my previous entry on using t-SNE for exploratory data analysis. Now we will consider t-SNE for use within a machine learning system.
Data visualisation gives very important insights about the data. But it is subjective to the goal of analysis & area of application. Let’s see how.
Lisa Spelman shares how businesses are benefiting from Intel’s flexible solutions for AI and how Intel is fostering the continued growth of the AI ecosystem.
In this blog post – “Part 1” – I address questions such as: How many ML and AI related patents were granted? Who are the most prolific inventors? The most frequent patent assignees? Where are inventions made? And when? Is the number of ML and AI related patents increasing over time? How long does it take to obtain a patent for a ML or AI related invention? Is the patent examination time shorter for big tech companies? etc. “Part 2” will be an in depth analysis of the language used in patent titles, descriptions, and claims, and “Part 3” will be on experimentation with with deep neural nets applied to the patents’ title, description, and claims text.