I give a lot of presentations. Before BeamWriter, involving the audience in impromptu polls, sharing additional information or getting questions from people online – or without having to pass a microphone around – could be anything from a hassle, to expensive to not possible.
BeamWriter was built to address this – make it super easy to involve the audience when giving a presentation or exhibiting at a trade show.
Once installed on your iPhone or iPad, creating an account and starting beaming takes a few minutes at most.
Your audience don’t have to log in – they pick up your Beam automatically when the app is running.
I now find that enriching my presentations and engaging my audience is easy enough that I don’t need an event team to support. I don’t need a bespoke polling solution or text-messaging solution for questions, and sharing a link to a copy of my presentation or collecting the email addresses of the audience, is feasible even when alone at a trade show.
You may not consider training your machine learning model on a mobile phone a very likely or viable approach. After all, a phone is a pretty limited computer, both in memory and processing capacity.
For some applications, where the size of say – a neural network – is limited, it could however, be extremely useful. Incremental improvements to a model that is specific to the individual user, could be made on the fly without incurring network overhead or the latency or cost from centralised processing. (The alternative would be to upload the data to the cloud, do the training there and re-download the trained model.)
To test this out we have implemented a classic neural network as a Swift class – SNNetwork.swift and powered it by our Matrix library (see this post). We have packaged SNNetwork with two other classes you will need – SMatrix.swift and MLGenerics.swift in a ‘try-it’ application; NNTester.
NNTester runs in Xcode on your Mac. It uses example data from MNIST for character recognition.
Each character is a 20 x 20 pixel matrix, unrolled into a 400 element vector where each pixel’s grayscale value is a Double. When you check out startTraining() in the MasterViewController class in NNTester, you will see that the neural network is created with a 400 (rather than 784 as in the illustration above) node input layer and a 10 node output layer.
Once trained, the neural network will take a 400 element input vector and produce a 10 element output, where the element with the highest value between 0 and 1 is interpreted as having the highest probability of being the input digit.
So if for instance, a handwritten digit is input as a 400 element pixel vector and the output vector is [0.01, 0.2, 0.05, 0.01, 0.005, 0.7, 0.003, 0.008, 0.004, 0.01], the element with the highest probability is the 6th, and the classifier would conclude that the input vector corresponds to a 6. Running a trained network in ‘feed-forward’ mode like this is done with a simple function call. If snnetwork is an instance of SNNetwork, then snnetwork.h(inputVector x : [Double]) -> [Double] will give you the ouput vector or ‘hypothesis’ given the x input vector.
Finally – don’t be confused by the fact that NNTester is a Mac application. By including SNNetwork.swift, SMatrix.swift and MLGenerics.swift in your iOS projects, you can start training or using pre-trained neural networks on the phone. SNNetwork contains code to save trained networks and read them in again, so you can also choose to train on the desktop and deploy the trained network to the phone.
The software is free for you to use as you please – we have released it under the GNU Lesser public license. If you want support from us – we are happy to provide that on commercial terms. Or if you would like to tell us how you have used the code, we would love to hear from you. Get in touch on email@example.com.