MCLNN improves music genre classification with automated feature exploration.
problem Music genre classification using neural networks.
method MCLNN uses a mask to enforce sparseness and learn time-frequency representations.
result MCLNN achieves competitive accuracy compared to state-of-the-art methods.
MCLNN improves audio classification with binary masks.
problem Improving audio classification accuracy.
method Binary mask applied to CLNN for feature preservation and combination exploration.
result Competitive recognition accuracies on GTZAN and ISMIR2004 datasets.
MCLNN improves music genre classification by learning frequency bands.
problem Classifying music genres using neural networks adapted from image recognition.
method MCLNN learns frequency bands, reducing susceptibility to frequency shifts and enabling concurrent exploration of feature combinations.
result MCLNN outperforms state-of-the-art Convolutional Neural Networks on the Ballroom music dataset.
MCLNN improves sound recognition by learning frequency bands.
problem Efficiently recognizing acoustic events from audio signals.
method MCLNN uses a binary mask to force sparseness in network weights, focusing on frequency bands.
result MCLNN achieves competitive performance in sound recognition compared to state-of-the-art methods.
MCLNN improves sound recognition by learning frequency bands.
problem Sound recognition from neural networks often misses environmental sound specifics.
method MCLNN incorporates filterbank behavior and automates feature combination exploration.
result MCLNN outperforms state-of-the-art methods on ESC-10 dataset.
MCLNN improves sound classification with fewer parameters.
problem Improving sound classification accuracy with fewer parameters.
method MCLNN uses a binary mask to induce sparseness in frequency bands, automating feature exploration.
result MCLNN achieves competitive results on Urbansound8k with 12% fewer parameters.
MCLNN improves sound event recognition with fewer parameters.
problem Improving sound event recognition with deep neural networks.
method Developed MCLNN to enforce sparseness and frequency shift invariance.
result MCLNN achieved competitive performance with 12% fewer parameters.
VoiceFilter separates target speaker from multi-speaker signals.
problem Speech recognition in multi-speaker environments.
method Speaker recognition network and spectrogram masking network trained together.
result Significant reduction in speech recognition WER on multi-speaker signals.
Study different masking schemes for a universal marginaliser.
problem Understand how well a neural approximator learns conditional distributions.
method Compare networks trained with various masking schemes.
result Neural approximators perform differently based on the masking scheme.
Develops masks to explain neural network predictions.
problem Improving neural network interpretability for various applications.
method Creates explanation masks for pre-trained networks using a secondary network.
result Demonstrates the effectiveness of the method across different types of networks.
StrNN uses neural network structures to learn conditional independencies.
problem Learning conditional independencies in neural networks.
method Designing masks for neural networks based on binary matrix factorization.
result StrNN improves density estimation and causal inference.
New unsupervised neural network for beamforming masks trained on real noisy speech.
problem Training neural beamforming masks without labeled data.
method Unsupervised training using a likelihood criterion from spatial mixture model.
result Performance comparable to supervised and teacher-trained systems.
Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.
problem Improving neural network performance through adaptive pruning of weights.
method Optimizes stochastic pruning masks by minimizing expected loss, considering data-adaptive regularization and feature alignment.
result Probabilistic fine-tuning leads to improved test error over baseline methods in neural networks.
Invertible neural networks with masked convolutions improve classification and generative models.
problem Building robust invertible neural networks for better model interpretability and generative tasks.
method Combining masked convolutions and iterative inversion methods to create invertible architectures.
result Invertible neural networks achieve competitive performance in classification and generative tasks.
Generates convincing swapped images of fashion articles on people.
problem Automatic swapping of clothing on fashion model photos.
method Conditional Analogy Generative Adversarial Network (CAGAN) based on adversarial training and deep convolutional neural networks.
result Plausible segmentation masks and convincing swapped images.
A new neural network approximates conditional distributions in generative models.
problem Inference in generative models with varying observation sets.
method Combining samples with a masking function and a neural network for amortized inference.
result Single neural network approximates all conditional marginal distributions efficiently.
NeuroMask provides interpretable explanations for deep neural networks.
problem Understanding how deep neural networks make decisions.
method Applies a mask to reveal or hide parts of an image, tuning mask values to preserve classification results and produce interpretable explanations.
result NeuroMask successfully localizes the most relevant parts of an image to a deep neural network's decision.
Transformers' self-attention mechanism is mapped to a generalized Potts model.
problem Uncertainty in what type of data distribution self-attention can efficiently learn.
method Decouple word positions and embeddings, then show self-attention learns a generalized Potts model.
result Training self-attention is equivalent to solving the inverse Potts problem.
Node Masking improves GNNs' scalability and generalization.
problem Improving GNNs' ability to handle arbitrary graphs.
method Introducing Node Masking to enhance GNNs' performance.
result Node Masking enables GNNs to generalize and scale better.
MARS automatically selects tensor decomposition ranks, improving performance in neural network tasks.
problem Determining optimal decomposition ranks in tensor decompositions.
method MARS uses binary masks to learn optimal tensor structure during training via relaxed MAP estimation.
result MARS achieves better results than previous methods in various tasks.
Paper proposes a new sparse Bayesian neural network for simpler, more efficient DNNs.
problem Complex and large DNN architectures require simplification for better performance and efficiency.
method Masked Bayesian Neural Networks (BNN) with nodewise sparsity and optimal posterior distributions.
result The proposed BNN yields well-condensed DNN architectures with similar accuracy and uncertainty quantification to large DNNs.
A technique scales symbolic methods with gradients for neural model explanation.
problem Limited scalability of symbolic methods for large neural networks.
method Combines gradient-based methods with symbolic techniques using Integrated Gradients to focus on a subset of neurons.
result Produces sparser and higher saliency regions compared to gradient-based methods alone.
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: ea…
Kernel method outperforms deep neural networks in speech enhancement.
problem Improving single-channel speech enhancement performance.
method Kernel regression with an exponential power kernel and EigenPro iterative method.
result Kernel method consistently outperforms deep neural networks in speech enhancement.
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
New method reduces diffusion model function evaluations for discrete data.
problem High computational burden in generating samples from masked diffusion models.
method Modified causal attention mask and speculative sampling mechanism for non-factorized predictions.
result Achieved ~2x reduction in required network forward passes.
Unified model combines feature and label propagation for semi-supervised classification.
problem Combining feature and label propagation for effective semi-supervised classification.
method Unified Message Passing Model (UniMP) using Graph Transformer and masked label prediction.
result Obtains new state-of-the-art results in Open Graph Benchmark (OGB).
A new deep neural network improves mammogram image processing.
problem Improving mammogram image processing accuracy and efficiency.
method A novel deep neural network architecture with dual-path connections.
result Achieves best mammography segmentation and classification results.
Differentiable Masking reveals how neural models make decisions across layers.
problem Intractable and expensive approximate search for input relevance in deep models.
method Differentiable Masking learns to mask inputs while maintaining differentiability.
result Reveals how decisions are formed across network layers in BERT models.
New method for efficient probabilistic inference using masked language modeling.
problem Efficient posterior inference in probabilistic programs with many hyper-parameters.
method Formulate inference as masked language modeling, train a neural network to unmask random values.
result Foundation posterior for zero-shot inference and fine-tuning across a range of programs.
A new method prunes neural network channels based on operation characteristics.
problem Compressing deep neural networks efficiently and maintaining accuracy.
method Differentiable masks for channel pruning considering BN and ReLU.
result Outstanding performance in accuracy with less resources compared to state-of-the-art methods.
A new method averages neural network parameters to rank features robustly.
problem Neural networks' sensitivity to random initialization affects feature ranking robustness.
method Parameter averaging of multiple shallow networks trained with different random seeds.
result The averaged model discovers ground-truth feature importance consistently.
Paper tackles catastrophic forgetting with task-based hard attention.
problem Catastrophic forgetting in neural networks after learning new tasks.
method Task-based hard attention mechanism learned through SGD.
result Reduces catastrophic forgetting by 45-80%.
Two CLEVER extensions improve neural network robustness evaluation.
problem Improving robustness evaluation of neural networks.
method Two extensions of CLEVER: second-order robustness guarantee and BPDA for non-differentiable inputs.
result Demonstrated effectiveness on a 121-layer Densenet model.
Graph Attention Networks use masked self-attention to improve graph neural networks.
problem Improving graph neural networks to better handle graph data.
method Stacked masked self-attention layers that allow nodes to attend to their neighborhoods with different weights.
result GAT models achieve state-of-the-art results across various graph benchmarks.
Quantized neural networks can improve robustness against adversarial attacks.
problem Adversarial attacks on neural networks with low-precision weights and activations.
method Proposed a third benefit of very low-precision neural networks: improved robustness against some adversarial attacks. Focused on weights and activations quantized to ±1, and conducted black-box and white-box experiments.
result Non-scaled binary neural networks can reduce the impact of iterative attacks, but do not artificially mask gradients.
Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
New taxonomy divides defense methods for neural networks.
problem Improving adversarial robustness of neural networks.
method Reframing existing defense categories into two new categories.
result There is no universal trade-off between robustness and accuracy.
Paper proposes energy-efficient DNN training methods.
problem Energy-constrained deployment of deep neural networks.
method Weighted sparse projection and layer input masking integrated into DNN training.
result Framework provides higher accuracy with same or lower energy budgets.
HM-NAS improves neural architecture search by learning optimal architectures.
problem Limited flexibility in architecture candidates due to hand-designed heuristics.
method Incorporates multi-level encoding and hierarchical masking to automatically learn optimal architectures.
result Achieves better architecture search performance and competitive model accuracy.
Quantized neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness of quantized neural networks.
method Investigated adversarial robustness of quantized neural networks under different threat models.
result Quantization does not offer robust protection and results in gradient masking.
BetaExplainer improves GNN interpretability by masking unimportant edges.
problem Interpreting GNNs' predictions is difficult due to black-box behavior and lack of uncertainty quantification.
method BetaExplainer uses a sparsity-inducing prior to mask unimportant edges during training.
result BetaExplainer provides uncertainty in edge importance and improves predictive accuracy on challenging datasets.
Simple iterative method reduces deep network size significantly.
problem Overparameterization of deep neural networks in compute-limited systems.
method Hybrid approach combining single shot pruning and Lottery-Ticket methods.
result State-of-the-art compression achieved with improved test accuracy and compression ratio.
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
Adaptive dropout and regularization are shown to be dual in linear networks.
problem Sparsifying deep neural networks.
method Examining dropout in the linear case, revealing a duality with regularization.
result Adaptive dropout methods lead to sparse solutions with effective penalties similar to classical sparse optimization penalties.
LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.
problem Scarce training data for hemorrhagic lesion segmentation.
method Lesion conditional Generative Adversarial Network (LcGAN) for synthetic image generation.
result Segmentation improved by 12.8% with synthetic data augmentation.
SMART training improves mask-predict translations.
problem Closing the performance gap between semi-autoregressive and autoregressive models.
method SMART training method for conditional masked language models.
result SMART-trained models produce higher-quality translations.
Parallel decoding improves machine translation efficiency and accuracy.
problem Efficiently generating translations from left to right.
method Conditional masked language modeling for parallel decoding.
result Improves translation performance by over 4 BLEU points.