Model learns to sort music clips in sequence.
problem Finding an optimal permutation of music clips.
method Proposed a music puzzle game for self-supervised learning of neural networks.
result Improved architecture (SEN) performs better on music medley.
Bardo Composer generates tabletop RPG music based on player speech.
problem Creating immersive background music for tabletop RPGs.
method Speech recognition, emotion classification, and music generation using a novel beam search algorithm.
result Generated music pieces can be accurately identified by human subjects as conveying the intended emotion.
GenéLive! generates rhythm game commands with musical structure.
problem Generating accurate rhythm commands in music games.
method Deep generative model that considers musical structures.
result Reduced business cost by half at KLab Inc.
Paper proposes using creative ML for game design.
problem Lack of creative ML in game design.
method Leverage existing creative ML systems for game content creation.
result Illustrates how creative ML can inform new game design systems.
Transformer adapts to multi-instrumental music generation using NES and Lakh MIDI datasets.
problem Generating multi-instrumental music scores with Transformers.
method Adapted Transformer architecture to multi-instrumental setting, used NES-MDB and Lakh MIDI datasets for pre-training.
result Pre-training with Lakh MIDI dataset improves performance for multi-instrumental music generation.
We consider a variant of the stochastic multi-armed bandit problem, where multiple players simultaneously choose from the same set of arms and may collide, receiving no reward. This setting has been motivated by problems arising in cognitive radio networks, and is especially challenging under the realistic assumption t…
Study explores reinforcement learning in a complex game environment, analyzing rule inference and policy learning.
problem Learning optimal policies in environments with hidden rules.
method Investigated using the Game Of Hidden Rules (GOHR) environment, employing Feature-Centric and Object-Centric state representations with a Transformer-based A2C algorithm.
result Transformer-based A2C models outperform traditional methods in GOHR, demonstrating the effectiveness of representation strategies.
Research adapts Multi-Armed Bandits for Minesweeper, improving player strategy.
problem Improving computational players' strategy in Minesweeper.
method Adapted Multi-Armed Bandit algorithms for Minesweeper.
result The approach was successful, especially on smaller game boards.
New puzzles from geometry and topology.
problem Exploring puzzles from geometric and topological concepts.
method Construction from square-tiled shapes, discussion of underlying mathematics.
result Puzzles naturally associated to puzzle spaces.
We analyze higher-dimensional sliding puzzles, finding solvability patterns.
problem Solvability of higher-dimensional cubical sliding puzzles.
method Study of puzzle graphs and token movement constraints.
result Characterization of solvability regimes from stuck to fully solvable.
Deep neural network predicts puzzle piece adjacency.
problem Jigsaw puzzle assembly accuracy.
method Deep learning model trained on pixel data.
result Significant improvement in puzzle assembly accuracy.
Model resolves asset pricing puzzles with price-impact.
problem Asset pricing puzzles like interest rate, stock-price volatility, and equity premium.
method Closed-form equilibrium model with exponential investors trading continuously and experiencing price-impact.
result Price-impact amplifies risk-sharing distortions, resolving puzzles.
Open geometry puzzles keep the author engaged.
problem Open problems in geometry that challenge the author.
method Collection of open problems based on puzzle-charm.
result No spare hands in solving the problems.
New distribution resolves excess volatility puzzle in finance.
problem Excess volatility in equity prices not explained by rational finance theory.
method Empirical analysis of historical returns using a new distribution.
result Volatility puzzle disappears when using a more appropriate return distribution.
Q*BERT learns to navigate text-based games by building a knowledge graph.
problem Text-based games have bottlenecks that standard RL agents struggle to overcome.
method Q*BERT learns a knowledge graph and uses intrinsic motivation to detect and overcome bottlenecks.
result Q*BERT outperforms state-of-the-art agents in text games, including Zork.
In this article we prove the impossibility of some disentanglement puzzles, first building mathematical models that reflect the essential characteristics of these puzzles.
JamBot generates music with LSTMs, producing pleasant chord progressions and polyphonic music.
problem Generating harmonious and structured polyphonic music.
method Two-step process: chord LSTM for chord progression, second LSTM for polyphonic music generation.
result JamBot's learned chord embeddings reveal the circle of fifths, a significant finding in music theory.
Model generates coherent polyphonic music using deep reinforcement learning.
problem Creating music that follows musical rules and coherence.
method Deep reinforcement learning architecture with a Bi-axial LSTM trained with a pseudo-kernel and DQN for exploration and coherence.
result The model generates polyphonic music that performs well quantitatively and qualitatively.
New system for automatic music emotion recognition considers multiple emotions simultaneously.
problem Automatic recognition of simultaneous and multiplicity of emotions in music.
method Comparison of multilabel and multiclass machine learning algorithms on the Emotify dataset.
result The Geneva Emotional Music Scale 9 is adopted for multilabel and multiclass classification of music emotions.
The paper categorizes music emotions and improves music retrieval.
problem Inefficient music retrieval based on album information.
method Categorical emotion expression, Fisher's separation theorem, feature extraction, Support Vector Machines.
result Maximum separability occurs between relaxing and epic music parts.
MuLan links music audio to natural language tags.
problem Traditional music tagging systems use rigid attributes; MuLan aims to link audio directly to natural language.
method Joint audio-text embedding model trained on 44 million music recordings and text annotations.
result MuLan's embeddings enable zero-shot functionalities and transfer learning.
Model generates music to connect missing parts, leveraging latent space of VAE.
problem Music inpainting from missing or lost information.
method Deep learning model using VAE latent space and RNN to traverse latent space conditioned on past and future musical contexts.
result Model generates meaningful music inpaintings, connecting musical excerpts.
MIDI-VAE models music dynamics and instrumentation for style transfer.
problem Modeling and transferring musical style across different instruments and dynamics.
method Variational Autoencoder (VAE) for polyphonic music modeling and style transfer.
result MIDI-VAE successfully transfers musical style between different genres and instruments.
BachProp generates music in various styles using deep learning.
problem Creating music algorithms that can adapt to multiple styles.
method Developed a novel music representation and trained a deep network to predict note transitions.
result BachProp generates music scores that better capture features of original corpora.
Trains word embeddings from music and text data to link music contexts.
problem Varying vocabulary size and musical relevance in word embeddings.
method Combines general text and music-specific data to train word embeddings.
result Trained embeddings better associate music contexts with compositions.
New model solves equity premium puzzle with risk aversion coefficient.
problem Equity premium puzzle in financial markets.
method Developed a new model incorporating investor risk behavior, tested with specific coefficients.
result Validated model with empirical studies, confirming coefficient of 1.033526.
We introduce Quintessence: a family of burr puzzles based on the geometry and combinatorics of the 120-cell. We discuss the regular polytopes, their symmetries, the dodecahedron as an important special case, the three-sphere, and the quaternions. We then construct the 120-cell, giving an illustrated survey of its geome…
Investors' strategic trading affects asset prices, modeled as a game.
problem Investors' trading rates influence asset prices in dynamic markets.
method Model as a non-zero sum singular stochastic differential game, establishing equivalence between best-response and auxiliary control problems.
result Unique Nash equilibrium is deterministic with a closed-form solution.
Generative models learn from high-level music representations, but this work models music in raw audio.
problem Capturing long-range correlations in music generation.
method Exploring autoregressive discrete autoencoders (ADAs) to model raw audio waveforms.
result Unconditional generation of piano music in raw audio domain with long-range correlations.
Music SketchNet generates missing measures in incomplete music pieces, guided by user input.
problem Generating missing measures in incomplete monophonic musical pieces.
method Introducing SketchVAE for factorized representation of rhythm and pitch, and two discriminative architectures for guided music completion.
result Our approach outperforms state-of-the-art models in both objective and subjective evaluations.
Dual-track model generates classical piano music better than other methods.
problem Generating inter-dependent piano music.
method Dual-track architecture with various neural network models and music representations.
result Proposed model outperforms other methods in evaluation.
DSHL generates music using segment concatenation and hash learning.
problem Music generation using deep learning.
method Deep recurrent neural network and ranking-based hash learning.
result DSHL generates original and enjoyable music.
New model solves equity premium puzzle.
problem Equity premium puzzle regarding risk behavior of investors.
method Developed a new tool called the sufficiency factor to analyze risk behavior of investors.
result Validated the new model with a coefficient of relative risk aversion of 1.033526.
Study shows trust and trustworthiness emerge through reinforcement learning.
problem Trust and trustworthiness are universal but not predicted by traditional economic models.
method Used Q-learning algorithm to simulate trust and trustworthiness dynamics in a trust game.
result High levels of trust and trustworthiness emerge when individuals consider both past and future experiences.
System composes polyphonic music using LSTM and RL.
problem Complex polyphonic music composition.
method Divided music into monophonic streams, trained LSTM to generate sequences, used RL to find pleasant compositions.
result System generates intricate melodies, chords, and contrapuntal sequences.
The study uses music chords to predict Brazilian music genres.
problem Classifying popular Brazilian music genres based on harmonic structures.
method Extracted and engineered harmonically related features from chords data, used random forest model for classification.
result Features from harmonic elements can predict Brazilian music genres.
Word2Vec captures musical relationships in complex polyphonic music.
problem Capturing meaningful relationships in musical contexts.
method Skip-gram version of word2vec applied to music slices from a large corpus.
result Word2Vec embeddings reveal functional chord and harmonic associations.
In his stimulating article on the reasons for two puzzling observations about the behaviour of interest rates, exchange rates and the rate of inflation, Charles Engel (2016) puts forward an explanation that rests on the concept of a non-pecuniary liquidity return on assets. Albeit intriguing the analysis struggles to a…
Adversarial autoencoder improves music latent space learning.
problem Learning effective latent spaces for symbolic music data.
method Adversarial regularization with Gaussian mixtures.
result MusAE outperforms standard VAEs in reconstruction and interpolation.
Bi-LSTM with attention generates jazz music with rich nuances.
problem Challenges in producing realistic music with structure and rationality.
method Deep learning, Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with Attention.
result Bi-LSTMs with attention preserve the richness and technical nuances of old style music.
Paper introduces a new model for polyphonic music composition.
problem Creating music with multiple interwoven voices.
method Developed a coupled recurrent model using probabilistic factorization and neural network ideas.
result Trained models for single-voice and multi-voice composition on a large dataset.
Generative model creates realistic dance poses from music.
problem Generating human-like dance poses from music.
method Music feature encoder, pose generator, music genre classifier integrated.
result Generative autoregressive model synthesizes dance sequences up to 5,000 frames.
Paper proposes GAN models for generating multi-track music.
problem Generating music with multiple tracks and temporal dynamics.
method Generative adversarial networks (GANs) for multi-track music generation.
result Models can generate coherent music of four bars right from scratch.
Paper applies GANs to symbolic music genre transfer.
problem Symbolic music genre transfer using GANs.
method CycleGAN architecture with additional discriminators to preserve structure.
result Fidelity of transformed music improved with additional discriminators.
Universal music translation network across instruments and genres.
problem Translating music across different instruments, genres, and styles.
method Multi-domain wavenet autoencoder with a shared encoder and disentangled latent space trained end-to-end on waveforms.
result Achieves convincing translations even from domains not seen during training.
Algorithm finds characteristic maps over complex shapes.
problem Finding non-singular characteristic maps over wedged simplicial complexes.
method Constructive puzzle algorithm based on linear algebra.
result Algorithm performs well compared to other methods.
This research improves neural synthesizers for music sounds from speech data.
problem Applying speech synthesis techniques to musical instrument sounds.
method Comparison of three neural synthesizers in three scenarios: training, zero-shot learning, and fine-tuning.
result Neural synthesizers trained on speech data and fine-tuned on music data perform better.
Anticipatory model generates music with control over events.
problem Controlling symbolic music generation.
method Interleaving event and control sequences to predict future events.
result Anticipatory model matches autoregressive models in performance and can infill control tasks.