Abstract I’d like to introduce you to this new, 60 year old, kid on the block: “Machine Learning”. Some math + some stats, but mostly “what”s, “why”s and “how”s of different problems it solves, and of course some code, since that’s what machines speak best. While we’ll ride along with mouthfuls such as “stochastic gradient … Read More
Over the past few weeks I’ve been experimenting with some basic machine learning. My task was to create a classifier for Slack messages. The application would be a slackbot that takes an input sentence and responds with whichever channel it believes the message should belong to. My bot only looks at three channels: #food, #fun, … Read More
Disclaimer: Some basic exposure to machine learning is assumed. Neural nets are on the rise, now that computing power and parallel data processing capabilities have reached the levels that allow them to shine. Recurrent neural nets, the more sophisticated kind that possess time dynamics, have achieved spectacular results in certain areas. Overfitting, however, has … Read More
I was lucky enough last week to attend PHLAI, a Comcast-sponsored conference on machine learning and artificial intelligence. The dreary weather did not dampen our spirits as practitioners and business stakeholders met to discuss one of the most important trends in our lifetime.
I recently attended the O’Reilly AI Conference in New York where artificial intelligence practitioners showcased the impressive strides they’ve made so far in using AI for real-world applications
The tech industry is in the middle of a massive, uncontrolled social experiment. Having made commercial mass surveillance the economic foundation of our industry, we are now learning how indiscriminate collections of personal data, and the machine learning algorithms they fuel, can be put to effective political use. Unfortunately, these experiments are being run in … Read More
In the last decade, a class of machine learning algorithms popularly know as “deep learning” have produced state-of-the-art results on a wide variety of domains, including image recognition, speech recognition, natural language processing, genome sequencing, and financial data among others. What is deep learning? Why has it become so popular so quickly? How can one fit deep learning into existing pipelines?
In the last decade, a class of machine learning algorithms popularly know as “deep learning” have produced state-of-the-art results on a wide variety of domains, including image recognition, speech recognition, natural language processing, genome sequencing, and financial data among others. What is deep learning? Why has it become so popular so quickly? How can one fit deep learning into existing pipelines?
Podcast: Play in new window | Download (Duration: 32:10 — 105.0MB) | Embed
As Mahout rolls towards a 1.0 release, Mahout committer and co-founder Grant Ingersoll, will provide an overview of what’s happening with the machine learning project and what to look forward to next.
Podcast: Play in new window | Download (Duration: 50:57 — 58.3MB) | Embed
In this episode, Joel warns us that the machines have started to learn on their own – and that maybe they can tell shredders apart from trashcans… Also, a great TechCrunch article on how you can now build dynamic grids of compute servers using Mesos and have them automatically bootstrapped and configured by Docker. We talk about CoreOS, which is a small linux distro for beginning machine configurations, the Genymotion android VM that everyone was talking about at AnDevCon2013, and more.