Stacked Capsule Autoencoders reconstruct objects from images using part relationships.
problem Reconstructing objects from images with robustness to viewpoint changes.
method Two-stage unsupervised capsule autoencoder that predicts part templates and object capsules.
result State-of-the-art results for unsupervised classification on SVHN and MNIST.
Proposes a new deep neural network training method using dictionary learning.
problem Training deep neural networks efficiently and effectively.
method Uses dictionary learning as the basic building block, stacking layers with features from shallower layers as inputs for deeper layers.
result Outperforms existing state-of-the-art techniques in benchmark problems and real-world applications like age and gender classification.
Deep learning model predicts stock market direction.
problem Forecasting stock market direction in finance.
method Stacked Denoising Autoencoder (SDAE) applied to financial prediction.
result Deep learning model outperforms traditional methods in predicting CSI 300 index.
A new method for DNNs using NMFs without BP.
problem Difficulties in finding appropriate parameters for DNNs.
method Alternating optimization with semi-nonnegative matrix factorizations.
result Similar error rates to conventional DNNs with BP.
This paper compares different deep learning techniques for feature learning from EHRs.
problem Extracting meaningful insights from high-dimensional, sparse clinical data.
method Uses stacked sparse autoencoders, deep belief networks, adversarial autoencoders, and variational autoencoders for feature representation.
result Variational autoencoders outperform other methods for large data sets, while stacked sparse autoencoders are superior for small data sets.
The paper compares different deep architectures for feature learning from EHRs.
problem Extracting meaningful insights from high-dimensional, sparse clinical data.
method Uses stacked sparse autoencoders, deep belief networks, adversarial autoencoders, and variational autoencoders for feature representation.
result Stacked sparse autoencoders perform better for small data sets, while variational autoencoders outperform for large data sets.
Autoencoders can learn generative models like mixtures of gaussians and sparse coding.
problem Learning generative models with autoencoders.
method Gradient descent on two-layer autoencoder architectures with shared weights.
result Autoencoders can recover parameters of generative models under certain conditions.
Proposes a deep learning method to estimate virtual battery parameters from end-use measurements.
problem Estimating virtual battery parameters from limited load information.
method Transfer learning based stacked autoencoder for deep network framework.
result Effectively estimates virtual battery parameters for different load ensembles.
RocketStack integrates predictions from multiple base learners using a recursive stacking architecture up to ten levels.
problem Feature redundancy, complexity, and computational burden in deep stacking.
method Level-aware recursive stacking with pruning and compression techniques.
result Increasing accuracy with depth and outperforming standalone ensembles at later levels.
Paper proposes a framework for disease prediction from EHRs with missing data.
problem Missing data in EHRs for disease prediction.
method Two-stage framework including missing data imputation and disease prediction using GANs and stacked autoencoders.
result Significantly improved disease prediction accuracy with AC-GAN and stacked autoencoder.
Optimal ANN pre-training with SDA reduces handwritten Bengali digit recognition error to 2.34%
problem Optimizing ANN architecture for Bengali handwritten digit recognition
method Pre-training ANN with stacked denoising autoencoder (SDA)
result Minimum validation error of 2.34% on handwritten Bengali dataset
SAERMA combines deep learning and rule mining to identify SNP interactions.
problem Identifying significant SNPs and their interactions in complex diseases.
method Stacked Autoencoder Rule Mining Algorithm (SAERMA) integrating deep learning and association rule mining.
result Achieved high classification accuracy (77% AUC, 77% SE, 68% SP) with 100 units.
Develops deep learning for efficient structured signal recovery.
problem Efficiently recovering structured signals from measurements.
method Introduces a deep learning framework for both linear and nonlinear measurements, learns structured representations from data, and uses stacked denoising autoencoders.
result Improves signal recovery performance compared to compressive sensing.
This work proposes a new method to train models with deep latent hierarchies using Optimal Transport.
problem Training models with deep latent hierarchies using VAEs often leads to the 'latent variable collapse' issue.
method Proposes a novel approach based on Optimal Transport to train models with deep latent hierarchies.
result The method avoids the 'latent variable collapse' issue and provides better sample generations and latent representation.
We investigate unsupervised pre-training of deep architectures as feature generators for "shallow" classifiers. Stacked Denoising Autoencoders (SdA), when used as feature pre-processing tools for SVM classification, can lead to significant improvements in accuracy - however, at the price of a substantial increase in co…
Automated feature extraction for bearing health monitoring.
problem Predicting mechanical faults in process industries to prevent shutdowns.
method Stacked autoencoder neural network and OSELM for automated feature extraction.
result 100% detection accuracy for bearing health states.
Study proposes a new method for MRI image reconstruction using denoising autoencoders and undecimated wavelet transforms.
problem Efficient MRI image reconstruction using under-sampled data.
method Undecimated wavelet transform, denoising autoencoder, proximal gradient algorithm.
result The proposed method enhances MRI image reconstruction efficiency and robustness.
Deep learning detects genetic interactions in type 2 diabetes.
problem Detecting genetic interactions in complex diseases like type 2 diabetes.
method Stacked Autoencoder for non-linear epistatic interactions.
result Deep learning can uncover missing heritability in complex diseases.
Extends VAEs to handle complex Bayesian network structures.
problem Handling complex dependency structures in Bayesian networks.
method Extends VAEs with graphical residual flows to model arbitrary dependency structures.
result Demonstrates improved performance on synthetic datasets.
New method extracts radio signal features for automatic modulation classification.
problem Challenges in automatic modulation classification without expert-defined features.
method Biologically-inspired regularized stacked sparse denoising autoencoders (SSDAs).
result Correct classification rates > 99% at 7.5 dB SNR and > 92% at 0 dB SNR.
A new deep learning tool learns multi-level dictionaries greedily.
problem Improving deep learning performance on benchmark datasets.
method Greedy learning of multi-level dictionaries, solving shallow dictionary learning problems sequentially.
result Our method outperforms other deep learning tools and state-of-the-art supervised dictionary learning methods.
Deep Learning predicts prognosis of AML cases using cytogenetics, age, and mutations.
problem Predicting prognosis of acute myeloid leukemia (AML) cases.
method Hierarchical Deep Learning model using autoencoders, trained on TCGA database.
result Achieved 83% accuracy in predicting prognosis of AML cases.
Improves unsupervised feature learning with an exclusivity concept.
problem Overfitting in AE-based unsupervised feature learning.
method Integrates exclusivity concept to enhance AE's latent feature representation.
result Significant improvement in performance compared to other methods.
All SMILES VAE learns molecule latent representations from SMILES strings.
problem Non-unique SMILES strings and high computational cost of graph convolutions hinder VAEs for molecular property optimization.
method Stacked recurrent neural networks encode multiple SMILES strings, pooling hidden representations, and attentional pooling builds a final latent representation.
result All SMILES VAE significantly surpasses state-of-the-art in molecular property optimization tasks.
DeepSign generates malware signatures with 98.6% accuracy.
problem Detecting new malware variants using conventional methods.
method Deep Belief Network (DBN) with denoising autoencoders.
result 98.6% classification accuracy on malware variants.
The paper analyzes how stacking improves model stability.
problem Lack of theoretical insight into how stacking works.
method Stability analysis of learning algorithms, focusing on hypothesis stability.
result The hypothesis stability of stacking is a product of base models and combiner.
We review the basic definition of a stack and apply it to the topological and smooth settings. We then address two subtleties of the theory: the correct definition of a ``stack over a stack'' and the distinction between small stacks (which are algebraic objects) and large stacks (which are generalized spaces).
Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. Bu…
In this article, we derive many properties of étale stacks in various contexts, and prove that étale stacks may be characterized categorically as those stacks that arise as prolongations of stacks on a site of spaces and local homeomorphisms. Moreover, we show that the bicategory of étale differentiable stacks and loca…
Constructs cohomology decompositions for symmetric stacks.
problem Cohomology of symmetric stacks.
method Constructs decompositions of cohomology, Borel--Moore homology, and vanishing cycle cohomology.
result Defines BPS cohomology and proves its equivalence to intersection cohomology for smooth stacks.
New neural stack and Turing Machine architectures prove stability and computational power.
problem Designing stable neural network architectures for Turing Machine simulation.
method Introducing neural stack and Turing Machine architectures, proving stability and computational equivalence.
result Differentiable nnTM with bounded neurons can simulate Turing Machine in real-time and is equivalent to UTM.
Bayesian stacking improves model performance with varying model weights.
problem Improving model predictions with heterogeneous input performance.
method Bayesian hierarchical stacking with varying model weights inferred via Bayesian inference.
result Hierarchical stacking yields better predictions than linear averaging.
This thesis explores geometric stacks and Poisson manifolds, proving new results in their classification and equivalence.
problem Classifying and understanding geometric stacks and Poisson manifolds.
method Rigorous proofs and new site constructions for geometric stacks and Poisson manifolds.
result Classification and equivalence results for b-symplectic manifolds.
Relates discrete group actions to orbit spaces as differentiable stacks.
problem Understanding dynamics of discrete groups on manifolds.
method Relating discrete group actions to orbit spaces as differentiable stacks.
result Orbit stack encodes dynamics up to conjugation and inversion.
Paper combines machine learning and model averaging for robust parameter estimation.
problem Estimating structural parameters with partially unknown functional forms.
method Pairing double/debiased machine learning with stacking for model averaging.
result DDML with stacking is more robust to unknown functional forms than single learners.
The paper extends parallel transport to stacks.
problem Parallel transport over stacks.
method Introducing parallel transport for principal bundles over differentiable stacks.
result Principal bundles with connections over stacks can be recovered from their parallel transport.
We generalize the notion of a small sheaf of sets over a topological space or manifold to define the notion of a small stack of groupoids over an étale topological or differentiable stack. We then provide a construction analogous to the étalé space construction in this context, establishing an equivalence of 2-categori…
Develops theory of differential graded schemes for derived stacks.
problem Creating a theory for derived stacks using dg schemes.
method Formulates dg schemes as homotopy sites, equates to stacks on dg algebras.
result Infinity category of stacks represented by dg schemes is derived schemes.
NN-Stacking improves predictive power of regression models by adjusting stacking coefficients with features.
problem Low predictive power of linear stacking methods.
method NN-Stacking uses neural networks to estimate adaptive stacking coefficients.
result NN-Stacking leads to better predictive power, especially in large datasets.
New category defined for differentiable stacks.
problem No specific problem stated; focuses on new definition.
method Introducing a new category definition.
result Established relation with Lie groupoid category.
Smooth stacks of orbifolds are shown to be infinite-dimensional orbifolds.
problem Understanding the structure of Hom-stacks of orbifolds.
method Using Lie groupoids and Fréchet-Lie groupoids to represent Hom-stacks.
result Hom-stacks of orbifolds are infinite-dimensional orbifolds.
For discrete data, the likelihood P(x) can be rewritten exactly and parametrized into P(X=x)=P(X=x∣H=f(x))P(H=f(x)) if P(X∣H) has enough capacity to put no probability mass on any x′ for which f(x′)=f(x), where f(⋅) is a deterministic discrete function. The log of the first factor giv…
This work characterizes global quotient stacks---smooth stacks associated to a finite group acting a manifold---among smooth quotient stacks [M/G], where M is a smooth manifold equipped with a smooth proper action by a Lie group G. The characterization is described in terms of the action of the connected componen…
The BPS decomposition theorem splits cohomology of symmetric stacks into invariant parts.
problem Decomposing the cohomology of smooth symmetric stacks into invariant parts.
method Using cohomological Hall induction and intersection cohomology of moduli spaces.
result Establishes the BPS decomposition theorem for various symplectic stacks.
A dynamic stacking method for network node classification.
problem Node classification on networks with varying topological features.
method Dynamic functional coefficients for heterogeneous classifiers.
result Significantly more accurate model for network node classification.
Constructs moduli stacks for quiver connections and extends non-Abelian Hodge theory.
problem Extending non-Abelian Hodge theory to moduli stacks of quiver connections.
method Formalizes and constructs moduli stacks of bundles with λ-connections over prestacks.
result Shows moduli stacks are algebraic and locally of finite presentation when base is smooth and projective.
Stacked conformal prediction simplifies model validation.
problem Validating stacked predictive models efficiently.
method Meta-learner at the top of a stacked ensemble for approximate marginal validity.
result The method achieves approximate marginal validity without a separate calibration sample.
Constructs equivariant cohomology models for differentiable stacks.
problem Developing cohomology theory for stacks with group actions.
method Extends classical results for smooth manifolds to differentiable stacks.
result Derives spectral sequences generalizing Bott's spectral sequence.