Posts tagged stochastic

“Everyone has observed the sonic phenomena of a political crowd of dozens or hundreds of thousands of people. The human river shouts a slogan in a uniform rhythm. Then another slogan springs from the head of the demonstration; it spreads towards the tail replacing the first. A wave of transition thus passes from the head to the tail. The clamour fills the city, and the inhibiting force of voice and rhythm reaches a climax. It is an event of great power and beauty in its ferocity. Then the impact between the demonstrators and the enemy occurs. The perfect rhythm of the last slogan breaks up in a huge cluster of chaotic shouts, which also spreads to the tail. Imagine, in addition the reports of dozens of machine guns and the whistle of bullets adding their punctuations to this total disorder. The crowd is then rapidly dispersed, and after sonic and visual hell follows a detonating calm, full of despair, dust and death. The statistical laws of these events, separated from their political or moral context… are the laws of the passage from complete order to total disorder in a continuous or explosive manner. They are stochastic laws.”

–Iannis Xenakis

Algorithmic music composition has developed a lot in the last few years, but the idea has a long history. In some sense, the first automatic music came from nature: Chinese windchimes, ancient Greek wind-powered Aeolian harps, or the Japanese water instrument suikinkutsu. But in the 1700s music became “algorithmic”: Musikalisches Würfelspiel, a game that generates short piano compositions from fragments, with choices made by dice.

Dice games, Markov chains, and RNNs aren’t the only ways to make algorithmic music. Some machine learning practitioners explore alternative approaches like hierarchical temporal memory, or principal components analysis. But I’m focusing on neural nets because they are responsible for most of the big changes recently. (Though even within the domain of neural nets there are some directions I’m leaving out that have fewer examples, such as restricted Boltzmann machines for composing 4-bar jazz licks, short variations on a single song, or hybrid RNN-RBM models, or hybrid autoencoder-LSTM models.)

via https://medium.com/artists-and-machine-intelligence/neural-nets-for-generating-music-f46dffac21c0?source=ifttt————–1