Living a few months in Cambridge: (red is day, blue is night)
I love the blue mass at the astronomy centre and the movie theatre. More random projects here.
An interesting statement: “neural networks use finitely many highly adaptive basis functions whereas gaussian processes typically use infinitely many fixed basis functions” - paraphrased from Wilson et al. 2015, based on work by MacKay, Neal and others.
Models seem to be constructed by making them likely in the light of data but not always such that they’re able to generate something similar. More ramblings about the likelihood.
I’ll try to give examples of efficient gaussian process computation here, like the vec trick (Kronecker product trick), efficient toeliptz and circulant matrix computations, RTS smoothing and Kalman filtering using state space representations, and so on.
Very untidy first working draft of the idea mentioned on the efficient computation page. Here, I fit a spectral mixture to some audio data to build a “generative model” for audio. I’ll implement efficient sampling later, and I’ll replace the arbitrary way this is trained with an LSTM-RNN to go straight from text/spectrograms to waveforms.
First of my experiments on audio modelling using gaussian processes. Here, I construct a GP that, when sampled, plays middle c the way a grand piano would.
… using Stan & HMC
A Minimal Working Example