Method decomposes neural signals into rhythmic and non-rhythmic components.
problem Analyzing complex neural signals with spatiotemporal dynamics.
method Linearized model of dynamic neural states, stochastic differential equations, Gaussian process regression.
result Demonstrates efficacy in identifying meaningful modulations of oscillatory signals.
RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
problem Efficiently learning rhythmic motion in reinforcement learning.
method Combining RNNs and SCN structures to create RCNs.
result RCNs outperform MLPs and SCNs across all environment tasks.
Paper compares XGB and BPNN for music style classification.
problem Efficient music style classification using different methods.
method Feature extraction for timbral texture, rhythmic content, and pitch content; comparative evaluation of XGB and BPNN.
result XGB outperforms BPNN for small datasets in music classification.
Transformer improves pop piano composition by incorporating beat-based structure.
problem Generating expressive pop piano compositions with coherent rhythmic structure.
method Improved data representation for Transformers, incorporating beat-bar-phrase structure.
result Composes pop piano music with better rhythmic structure than existing models.
Deep learning improves cECG denoising for better cardiac health monitoring.
problem Motion artifacts limit the clinical use of cECG for long-term monitoring.
method End-to-end deep learning architecture trained on motion-corrupted cECG and reference ECG.
result MSE of 0.167 and Cross Correlation of 0.476 for signal denoising.
Generates music with coherent rhythm, chords, and melody using LSTM models.
problem Lack of direction and coherence in generated music by neural networks.
method Two-stage LSTM model: first generates harmonic and rhythmic templates, then melodies conditioned on these.
result Subjective test shows improved musical coherence and coherence compared to baselines.
New method learns complex brain signal patterns from EEG/MEG data.
problem Complex waveforms in brain signals not captured by linear filters.
method Multivariate convolutional sparse coding (CSC) algorithm.
result Reveals non-sinusoidal mu-shaped patterns in brain signals.
Machine learning identifies Shakespeare and Fletcher's contributions to Henry VIII.
problem Determining the relative contributions of Shakespeare and Fletcher in Henry VIII.
method Combined analysis of vocabulary and versification with machine learning techniques.
result Supports canonical division and new modifications of Henry VIII's authorship.
Paper teaches robots to play piano with touch and learning.
problem Teaching robots to play piano with touch and emotion.
method Reinforcement learning from scratch with touch-augmented reward and curriculum.
result Robots can play piano with correct key positions and various requirements.
Neural network generates music scores directly from polyphonic audio.
problem Transcribing music scores directly from polyphonic audio.
method Convolutional Recurrent Neural Network (CRNN) with CTC loss function.
result Model can learn to transcribe scores directly from audio signals.
The paper models musical motif transformations in Beethoven's works.
problem Understanding how motifs transform in symbolic music.
method Developed a probabilistic framework using Conditional Random Fields.
result Identified patterns of motif transformations and their co-occurrences.
Study limits of circadian synchronization under different light signals.
problem Disruption of circadian rhythms due to misalignment with external light signals.
method Matrix-free approach for locating periodic steady states, numerical continuation, bifurcation diagrams, unsupervised learning.
result Limits of circadian synchronization to external light signals of different frequency and duty cycle.
Unified model for audio control and style transfer.
problem Explicit control and style transfer in music generation.
method Diffusion autoencoders for semantic feature extraction, disentanglement using adversarial criterion.
result Model generates audio matching timbre targets with specified structure.
The starting point of this article is the question "How to retrieve fingerprints of rhythm in written texts?" We address this problem in the case of Brazilian and European Portuguese. These two dialects of Modern Portuguese share the same lexicon and most of the sentences they produce are superficially identical. Yet t…
A new method selects multiple activation functions at each layer of a neural network.
problem Selecting an adequate activation function requires trial and error.
method Activation Ensembles: introduces additional variables α to allow for multiple activation functions at each neuron. result Achieves superior results compared to traditional techniques.
This paper studies activation sparsity in large language models, finding key trends and implications.
problem Activation sparsity in large language models (LLMs) can be improved for efficiency and interpretability.
method Proposes PPL-p% sparsity, analyzes trends with training data, width-depth ratio, and parameter scale. result ReLU is more efficient for sparsity than SiLU, and deeper architectures can improve sparsity.
Study uses HMM for real-time activity recognition from sensor data.
problem Real-time activity recognition from streaming sensor data.
method Online hierarchical hidden Markov model.
result Improved activity recognition accuracy compared to existing methods.
Drop-Activation reduces overfitting by randomly setting activations to identity.
problem Overfitting in deep learning models.
method Randomly sets activations to identity during training and uses a deterministic network during testing.
result Improves generalization and performance of neural networks.
Adapts neural network neurons' activation functions for better predictions.
problem Training neural networks with fixed activation functions limits their performance.
method Proposes training over a shape parameter, allowing neurons to adapt their own activation functions.
result Improves prediction accuracy by allowing neurons to tune their activation functions.
Proposes bipolar activation functions to shift layer mean activations towards zero.
problem Training deep neural networks with high layer mean activations.
method Extends ReLU-family activation functions to shift mean activations towards zero.
result Improves language modeling and classification tasks with competitive results.
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
Active learning method balances bias and variance under class imbalance.
problem Active learning under label shift when class proportions differ.
method Mediated Active Learning under Label Shift (MALLS) using a 'medial distribution'.
result MALLS reduces asymptotic sample complexity under arbitrary label shift.
New method learns neural network activation functions from data.
problem Learning activation functions for neural networks.
method Model each neuron's activation function as a small neural network.
result Learned activation functions improve network performance.
Study active learning of PTFs with derivative access.
problem Active learning of polynomial threshold functions (PTFs).
method Algorithm for active learning degree-d univariate PTFs with derivative access. result Computational efficient algorithm for active learning degree-d univariate PTFs. Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…
Paper proposes algorithms for active learning of reject option classifiers.
problem Active learning of reject option classifiers is unaddressed in machine learning.
method Developed novel algorithms using double ramp and double sigmoid loss functions.
result Proposed algorithms efficiently reduce the number of labeled examples required.
Bayesian adaptive designs can be biased by active learning, especially with misspecified models.
problem Active learning bias in Bayesian adaptive experimental designs.
method Analysis of linear and preference learning models, empirical testing.
result Model misspecification and noise influence active learning bias in Bayesian designs.
RAN model recognizes multiple activities from unlabeled sensor data.
problem Handling weakly labeled multi-activity data from wearable sensors.
method Recurrent Attention Networks (RAN) for sequential multi-activity recognition and localization.
result RAN model can infer multiple activities and determine activity locations from unlabeled data.
Derives time-averaged active inference from control principles.
problem Finite-horizon or discounted-surprise problems in active inference.
method Derives infinite-horizon, average-surprise active inference from optimal control principles.
result Unified objective functional for sensorimotor control.
Study binary activated deep neural networks using PAC-Bayesian theory.
problem Generalization bounds for binary activated deep neural networks.
method Developed an end-to-end framework and provided PAC-Bayesian generalization bounds.
result Nonvacuous PAC-Bayesian generalization bounds for binary activated deep neural networks.
A new indicator measures project risk from activity durations.
problem Managing project risks throughout the lifecycle.
method Activity Risk Index (ARI) based on Schedule Risk Baseline.
result Identifies activities contributing most to project uncertainty.
D-CSC framework reveals how ReLU activation functions recover activation paths in neural networks.
problem Understanding how ReLU activation functions recover activation paths in neural networks.
method Deep Convolutional Sparse Coding (D-CSC) framework, omitting dictionary learning, to analyze activation paths.
result Uniform guarantees for recovery of true activation paths with high probability for greater activation densities.
Recognizes collective sheep movement activities online.
problem Recognizing collective animal movement activities.
method Discriminative framework for tracking flock positions and velocities online.
result Good accuracy in learning skewed collective activities.
Hidden Markov Models detect hand gestures from wearable sEMG signals.
problem Detecting activity regions in continuous sEMG signals.
method Hidden Markov Models applied to sEMG signals for gesture recognition.
result Average accuracy of 96.25% for activity onsets and 87.5% for activity terminations.
Risk-aware active learning reduces generalization error.
problem Learning policies with minimal performance risk.
method Risk-aware active inverse reinforcement learning algorithm.
result Risk-aware active learning outperforms standard approaches.
Active testing reduces label costs for efficient model evaluation.
problem Real-world applications require expensive test labels, disconnecting from existing model evaluation methods.
method Derives acquisition strategies to select test points efficiently, addressing label bias and variance.
result Active testing improves model evaluation efficiency without sacrificing accuracy.
Deep neural networks with various activation functions can approximate Hölder smooth functions.
problem Expressivity of deep neural networks with general activation functions.
method Investigates approximation ability of deep neural networks with a broad class of activation functions, including Hölder smooth functions.
result Derives the required depth, width, and sparsity of deep neural networks to approximate Hölder smooth functions.
Paper presents a novel online HAR method using Hierarchical Hidden Markov Models.
problem Challenges in robust online activity recognition in smart environments.
method Two-phase approach: 1) Segmentation and activity reporting using Hierarchical Hidden Markov Models, 2) Correction of labels based on statistical features.
result Proposes a method that can detect and correct interrupted activities, outperforming state-of-the-art methods.
New method finds best neural architecture during learning.
problem Active learning of deep neural networks with known architectures.
method Neural architecture search during active learning.
result Outperforms fixed architecture active learning.
Survey of trainable activation functions in neural networks.
problem Improving neural network performance through trainable activation functions.
method Taxonomy and comparison of recent and past models of trainable activation functions.
result Many trainable activation functions are equivalent to adding neuron layers with fixed activation functions and simple constraints.
Generative Adversarial Active Learning improves learning speed by synthesizing queries.
problem Efficiently increase learning speed in machine learning models.
method Uses Generative Adversarial Networks (GAN) to adaptively synthesize training instances.
result The proposed algorithm outperforms traditional methods in some settings.
This paper analyzes and improves active learning techniques for real-world projects.
problem Reducing labelling effort in machine learning models with real-world constraints.
method Systematic study of active learning issues, proposing techniques to address model convergence, annotation error, and dataset imbalance.
result Presentation of two techniques to speed up active learning: partial uncertainty sampling and larger query size.
ABUs learn and adapt activation functions for deep neural networks.
problem Lack of a unified theory connecting task and network properties with activation functions.
method Introduce Adaptive Blending Units (ABUs) as a trainable linear combination of activation functions.
result Advantages of ABUs over common activation functions across various network specifications.
Dynamic ensemble active learning tackles non-stationary criteria in active learning.
problem Active learning's effectiveness varies across datasets and sessions, leading to suboptimal results.
method Developed a dynamic ensemble active learner based on a non-stationary multi-armed bandit with expert advice.
result Dynamic ensemble selects the best criteria at each step, improving overall performance.
Study active nematic forces on curved surfaces, revealing new coupling mechanisms.
problem Understanding active nematic forces on curved surfaces.
method Developed a thermodynamically consistent surface model with nematic activity, analyzed topological defects.
result Active defects contribute both tangential and normal forces on curved surfaces.
Bayesian active learning method improved for censored regression data.
problem Challenges in estimating BALD for censored regression data.
method Derived entropy and mutual information for censored distributions, developed C-BALD objective, proposed novel modelling approach. result Demonstrated C-BALD outperforms other methods in censored regression. This paper provides an overview of activation functions in neural networks.
problem Confusion in activation function selection and properties in deep learning.
method Analytic review of popular activation functions.
result Clarification of activation function properties and selection.