We investigate how machine learning models acquire the ability to compose music and how musical information is internally represented within such models. We develop a composition algorithm based on a restricted Boltzmann machine (RBM), a simple generative model capable of producing musical pieces of arbitrary length. We convert musical scores into piano-roll image representations and train the RBM in an unsupervised manner. We confirm that the trained RBM can generate new musical pieces; however, by analyzing the model's responses and internal structure, we find that the learned information is not stored in a form directly interpretable by humans. This study contributes to a better understanding of how machine learning models capable of music composition may internally represent musical structure and highlights issues related to the interpretability of generative models in creative tasks.

One practical problem when using a RBM is that we need to decide the size of the hidden layer (number of hidden units) before performing learning, and it can be challenging to decide what is the optimal size. One simple heuristic is to search the'best" number of hidden units using cross

We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions.

GibbsNet is the best of both worlds both in theory and in practice.

We demonstrate APM's ability to recognize

An EBM is the only object that needs to be trained and designed. Separate networks are not tuned to ensure balance (for example, [He et al., 2019] point out unbalanced training

Objects are composed of a set of geometrically organized parts.

AI'godmother' Fei-Fei Li says she is'proud to be different' The'godmother' of AI, Professor Fei-Fei Li has told the BBC that being the only woman amongst seven pioneers of artificial Intelligence being presented with a top engineering prize by the King today makes her proud to be different. The King will present the 2025 Queen Elizabeth Prize for Engineering to Prof Li and six others during a ceremony at St James's Palace. Those honoured alongside her are Prof Yoshua Bengio, Dr Bill Dally, Dr Geoffrey Hinton, Prof John Hopfield, Nvidia founder Jensen Huang and Meta's Chief AI Scientist Dr Yann LeCun. They are being recognised for their contributions to the development of modern machine learning, a field that underpins the rapid advancement of AI. Who are the Godparents of AI? Dr Hinton, Prof Bengio and Yann LeCun, currently Chief AI Scientist at Meta have widely been recognised as the Godfathers of AI since they were jointly awarded the 2018 Turing Award.

We demonstrate APM's ability to recognize

An EBM is the only object that needs to be trained and designed. Separate networks are not tuned to ensure balance (for example, [He et al., 2019] point out unbalanced training