Shayaan Abdullah

Recent Posts

To Build a Smarter Chatbot, First Teach It a Second Language

Posted by Shayaan Abdullah on 10/4/17

This blog post was originally posted on MIT Technology Review by Will Knight

From Alexa and Siri to countless chatbots and automated customer support lines, computers are gradually learning to talk. The only trouble is they are still very easily confused.

A research team at Salesforce has come up with a clever way to improve the performance of many modern language programs—teaching an algorithm to speak another language before training it to do other tasks.

Read More

Topics: Artificial Intelligence, Machine Learning, Sentiment Analysis

How Neural Networks Think

Posted by Shayaan Abdullah on 9/20/17

This blog post was originally posted by Larry Hardesty on MIT News.

Artificial-intelligence research has been transformed by machine-learning systems called neural networks, which learn how to perform tasks by analyzing huge volumes of training data.

During training, a neural net continually readjusts thousands of internal parameters until it can reliably perform some task, such as identifying objects in digital images or translating text from one language to another. But on their own, the final values of those parameters say very little about how the neural net does what it does.

Read More

Topics: Artificial Intelligence, Neural Networks

MILABOT and the Amazon Alexa Prize Competition

Posted by Shayaan Abdullah on 9/18/17

In 2016 Amazon inaugurated the Alexa Competition dedicated to “accelerating the field of conversational AI”, with the winner to be determined in late 2017. As part of the competition, university research teams attempted to build a socialbot that could converse coherently and engagingly with humans on popular topics for 20 minutes.

Read More

Topics: Artificial Intelligence, Deep Learning, Machine Learning, Reinforcement Learning, natural language processing