I-Spy (using Watson services from Scratch projects)

February 22nd, 2017

It’s half-term week, so that means more time for geekiness with the kids.

This is something Grace made this week: a game of “I spy” built using Scratch, that uses the Watson Vision Recognition API to let the game dynamically pick objects that it recognises in photos, so you can then make guesses.

Apart from being a fun game to make in it’s own right, I wanted to share why I particularly think it’s useful to be able to use Watson API’s from Scratch projects.

Screen Shot 2017-02-22 at 13.43.53

Read the rest of this entry »

Will AI destroy the human race? A debate at The Arts Club

February 20th, 2017


The Arts Club Debating Society – Robots Will Destroy The Human Race from The Arts Club on Vimeo.

Aidan Laverty, Murray Shanahan, Ian Yorston, George Zarkadakis, and me.

This was a weird evening.

Read the rest of this entry »

Owlbot: Faith’s first chatbot (and barcamp)

November 13th, 2016

For her talk at Barcamp Southampton yesterday, Faith did a presentation on owls, together with a chatbot she trained to answer questions about owls.

I’ve brought Grace to a couple of barcamps with me before: Barcamp Berkshire and Barcamp Bournemouth. But this was Faith’s first time.

She decided that she wanted to do a talk on owls. That wasn’t a big surprise… she’s a little bit obsessed with owls.

Some of Faith's owls

Read the rest of this entry »

Machine learning “Top Trumps”

October 1st, 2016

A simple demonstration of machine learning to let a child train a computer to play Top Trumps

I’ve been talking for a while now about how we introduce the idea behind machine learning to school kids. I’ve given several talks about it but I’ve also tried out a couple of approaches to it.

Now I’m trying out another: training a machine learning bot how to play Top Trumps.

I’ve put a demo at toptrumps.eu-gb.mybluemix.net.

screenshot

What is this?

It’s basically Top Trumps: that card game I used to play as a kid where you choose one of the attributes on a card, and if it beats the other player you get their card. Except it’s online, and you’re playing against a computer.

But the computer hasn’t been given any strategies on how to play, and has to learn from the player.

Initially, it makes random choices, but it learns from playing against the player. The more turns it plays, the more training it gets, which it uses to make predictions of which choice would give it the best chance of winning. Read the rest of this entry »

A night at the museum

August 25th, 2016

I shared this at the time on twitter, and then went off on holiday. Now we’re back, I thought it’s worth sharing a little more.

I took Grace and Faith to the Natural History Museum in London, and we had a sleepover! It’s something they do for kids aged 7-11, called Dino Snores for Kids.

Read the rest of this entry »

Normalised Discounted Cumulative Gain

July 15th, 2016

A ramble about accuracy compared with NDCG scores for evaluating effectiveness of information retrieval. It’s an introduction, so if you already know what they are, you can skip this.

A couple of weeks ago, we released a new tool for training the IBM Watson Retrieve and Rank service (a search service that uses machine learning to train it how to sort search results into the best order).

This afternoon, I deployed a collection of small updates to the tool and thought I’d make a few notes about what’s changed.

Most of them are a bunch of incremental updates and minor bug fixes.

For example, support for a wider range of Bluemix environments, support for larger document cluster sizes, displaying the amount of disk space left in a cluster, and so on.

One update in particular I thought was more interesting, and worth explaining.

Read the rest of this entry »

IBM Watson Retrieve and Rank tool

June 30th, 2016

A few months ago, I mentioned that I was starting a new project. In this post, I’ll explain what we’ve been working on and what we’re trying to achieve with it.

The project was to build something new: a self-serve web-based tool to enable training the IBM Watson Retrieve and Rank service.

Earlier today, we released a first version of the tool. Now it’s finally out there, I can share what I’ve been working on!


My video walkthrough of the IBM Watson Retrieve and Rank tool

Read the rest of this entry »

Watson Rock, Paper, Scissors

June 26th, 2016

A simple hands-on activity to let kids train a machine learning classifier to be able to play Rock, Paper, Scissors.

Screen Shot 2016-06-26 at 13.59.20

I’ve written and spoken before that I think we should do more to introduce children to the idea of machine learning. And I’ve tried introducing my two kids to it, such as by making a Code Club-style game with them: we built a system to play Guess Who, that they trained both to understand what you say and to recognise the characteristics of faces from photos.

This weekend, we tried out another idea – Rock, Paper, Scissors from a web app, using the web cam to see your moves, and training a system to recognise your hand signs.

DSC06146

Read the rest of this entry »