Algoriffix Blog

Category: Origins

  • Towards Nonnegative Autoencoders

    Deep convolutional architectures with multiplicative factor updates.

    Deep learning did not emerge from a single breakthrough. Long before today’s large-scale AI systems became dominant, researchers were already exploring multilayer representations, convolutions, sparse coding, and hierarchical feature extraction across several overlapping research traditions (see also Before Music AI Became a Commodity).

    (more…)

  • Before Music AI Became a Commodity

    From acoustic vocabularies to online musical inference.

    Today, much of music AI is dominated by very large models trained on enormous datasets. In many cases, these systems treat audio primarily as a statistical prediction problem: enough data, enough parameters, enough compute, and useful behaviour eventually emerges.

    (more…)