Bayesian deep learning integrates perception and inference for higher-level intelligence.
problem Integrating perception and inference for tasks requiring higher-level intelligence.
method Unified probabilistic framework combining deep learning and Bayesian models.
result Integrating perception and inference leads to improved performance in tasks like recommender systems and topic models.
Bayesian deep learning integrates deep learning and probabilistic models for better inference.
problem Higher-level inference using probabilistic models is more powerful than deep learning alone.
method Unified probabilistic framework combining deep learning and Bayesian models.
result Bayesian deep learning enhances both perception and inference processes.
The paper learns robot skills from demonstrations without supervision.
problem Discovering robotic options from unlabelled demonstrations.
method Temporal variational inference for latent variable learning.
result The framework can learn options across multiple datasets.
New framework identifies causal models with arbitrary interventions, improving realism.
problem Identify causal models with realistic interventions.
method Theoretical framework for identifying causal models with arbitrary interventions.
result Identify causal models with arbitrary interventions, up to a higher-level abstraction.
Factor analysis provides linear factors that describe relationships between individual variables of a data set. We extend this classical formulation into linear factors that describe relationships between groups of variables, where each group represents either a set of related variables or a data set. The model also na…
Variational method learns disentangled latent factors from unlabeled data.
problem Learning disentangled latent factors from unlabeled data.
method Variational inference with a disentanglement regularizer and metric.
result Significant improvement in disentanglement and data likelihood.
This research explores inductive biases for deep learning to improve AI's higher-level cognition.
problem Current AI struggles with flexible out-of-distribution and systematic generalization.
method Examines and proposes new inductive biases for deep learning.
result Identifies specific inductive biases for higher-level sequential processing.
Introduces Motion Programs for better video analysis of human motion.
problem Current video analysis focuses on raw pixels or keypoints, missing higher-level motion primitives.
method Introduces Motion Programs as a neuro-symbolic representation of motions as a composition of high-level primitives.
result Motion Programs accurately describe diverse human motions and improve downstream tasks.
A new method for solving complex sequential decision-making problems by decomposing them into multiple levels.
problem Sequential decision-making with natural multi-level structure.
method Multi-level meta-reinforcement learning with skill-based curriculum.
result Efficiently reduces stochasticity and policy search space, leading to fewer iterations and computations.
A new method learns to segment and represent objects jointly without supervision.
problem Learning to segment and represent objects jointly without supervision.
method Iterative variational inference for disentangled object representations.
result System learns to inpaint occluded parts and extrapolates to unseen objects.
DSVM model predicts financial market volatility with better accuracy.
problem Predicting financial market volatility accurately.
method Deep latent variable models with variational inference.
result DSVM outperforms GARCH models in predicting volatility.
HiPPO adapts skills and higher-level policies together for better transfer in hierarchical RL.
problem Sub-optimality in skill transfer when lower-level skills are fixed.
method HiPPO: a novel hierarchical policy gradient method that trains all levels of the hierarchy jointly.
result Improved robustness of skills to environment changes through training time-abstractions.
Enhances reinforcement learning with hierarchical policies using latent variables.
problem Improving performance in reinforcement learning tasks with hierarchical policies.
method Training each layer of a hierarchical neural network to solve tasks directly, with latent variables controlling lower layers.
result Improves performance on standard benchmark tasks and complex sparse-reward tasks.
AIF improves physical AI agents' performance in dynamic environments.
problem Physical AI agents are less capable than biological agents in open-ended real-world environments.
method Developed from probability theory, Bayesian machine learning, variational inference, and Active Inference (AIF), grounded in the Free Energy Principle.
result AIF minimizes variational free energy and is well-suited to physical constraints.
LYRICS integrates deep learning and logic inference for complex decision-making.
problem Combining deep learning with symbolic logic for intelligent decision-making.
method LYRICS provides a generic interface layer that integrates TF models with FOL knowledge, converting constraints into optimization problems.
result LYRICS enables learning under logical constraints, improving model performance and decision-making.
Fuzzy eIX method evolves classifiers for online data streams.
problem Handling time-varying classifiers in online data streams.
method Develops evolving Internal-eXternal Fuzzy granules for numerical data.
result Fuzzy eIX maintains high accuracy in dynamic scenarios.
The paper develops methods for causal function estimation and inference with multiway clustered data.
problem Estimation and inference for causal functions under multiway clustering.
method Two-step procedure using machine learning for nuisance parameters and projection onto basis functions.
result Rejects the null hypothesis of uniformly zero effects and reveals heterogeneous treatment effects.
A network supporting deep unsupervised learning is presented. The network is an autoencoder with lateral shortcut connections from the encoder to decoder at each level of the hierarchy. The lateral shortcut connections allow the higher levels of the hierarchy to focus on abstract invariant features. While standard auto…
AuGMEnT network struggles with long-term memory for hierarchical tasks.
problem Learning and memory in neural networks, especially hierarchical tasks.
method Introduced hybrid AuGMEnT with leaky and non-leaky memory units.
result Hybrid AuGMEnT solves hierarchical and distractor tasks.
Torch-Points3D simplifies 3D deep learning research and reproducibility.
problem Lack of transparency and reproducibility in 3D deep learning research.
method Modular framework with quality-of-life features, standardized protocols, and open-source implementation.
result Facilitates fair and rigorous evaluation of 3D deep learning methods.
Generative model for scalable vector graphics captures font design statistics.
problem Lack of higher-level understanding in vision and imagery modeling.
method Sequential generative models of vector graphics.
result Model captures statistical dependencies and richness of font datasets.
We propose dynamical systems trees (DSTs) as a flexible class of models for describing multiple processes that interact via a hierarchy of aggregating parent chains. DSTs extend Kalman filters, hidden Markov models and nonlinear dynamical systems to an interactive group scenario. Various individual processes interact a…
RICH models scenes as hierarchical tree to learn and generate complex compositions.
problem Learning compositional structures between parts and objects in natural scenes.
method RICH uses a latent scene graph to organize entities into a tree structure and employs a top-down inference approach.
result RICH learns and generates complex scene hierarchies from unlabeled data.
Reviews Gaussian Markov models for conditional independence.
problem Understanding conditional independence in probabilistic models.
method Historical review of model selection and estimation techniques.
result Gaussian Markov models are similar but not equivalent to each other.
Bayesian VI copula models capture asymmetric intraday equity dependence.
problem Modeling asymmetric and extreme tail dependence in financial data.
method Bayesian variational inference for skew-t copula models in high dimensions.
result The copula captures substantial heterogeneity in asymmetric dependence over equity pairs and time.
An efficient way to learn deep density models that have many layers of latent variables is to learn one layer at a time using a model that has only one layer of latent variables. After learning each layer, samples from the posterior distributions for that layer are used as training data for learning the next layer. Thi…
This work improves generative models by using feedback from multiple dependent models.
problem Improving the performance of generative models in multi-agent systems.
method Building a hierarchical set-up of multiple dependent generative models and using feedback to improve lower-level models.
result The technique improves the performance of lower-level generative models under certain conditions.
Paper introduces Prob-SSI for robust OMA in noisy data.
problem Challenges in estimating modal parameters from noisy data.
method Probabilistic formulation of SSI, robust Prob-SSI algorithm.
result Robust Prob-SSI outperforms conventional SSI in corrupted data.
Improved deep learning models using new attribution priors and expected gradients.
problem Improving interpretability and performance of deep learning models.
method Introducing new attribution priors and expected gradients method that satisfies interpretability axioms.
result Improves model performance across various real-world tasks.
New measures quantify dependence between variables without distribution estimation.
problem Measuring dependence between variables in arbitrary dimensions.
method Proposed matrix-based normalized total correlation and dual total correlation measures.
result Measures are differentiable and statistically more powerful than existing methods.
We consider the problem of modelling noisy but highly symmetric shapes that can be viewed as hierarchies of whole-part relationships in which higher level objects are composed of transformed collections of lower level objects. To this end, we propose the stochastic wreath process, a fully generative probabilistic model…
Proposes methods to improve hierarchical classification accuracy by flattening inconsistent nodes.
problem Error propagation in top-down hierarchical classification due to inconsistent nodes.
method Data-driven approaches for identifying and flattening inconsistent nodes.
result Improves classification performance by up to 7% in Macro-F1 score.
A novel hierarchical Bayesian approach to Federated Learning reduces data exposure and improves convergence rates.
problem Data privacy and convergence in Federated Learning.
method Hierarchical Bayesian modeling and block-coordinate descent optimization.
result The proposed algorithm converges to an optimal solution with a rate of O ( 1 / t ) O(1/\sqrt{t}) O ( 1/ t ) and guarantees vanishing generalization error. Neural network learns to focus on slowly varying latent parameters in time series data.
problem Extracting slowly varying latent parameters from time series data.
method Transform raw data into a higher-level categorical representation, train predictor from new time series to future, introduce non-triviality measure.
result Creates a coarse-grained model focusing on latent parameters, capable of semi-supervised learning.
This study compares feature extraction methods using Neural Networks and Latent Dirichlet Allocation for movie synopses.
problem Extracting meaningful features from movie synopses for pattern detection and recommendation.
method Employed Latent Dirichlet Allocation for topic modeling and Neural Networks for distributed paragraph representations.
result Latent Dirichlet Allocation can provide meaningful features for movie synopses, comparable to Neural Networks.
FCN improves lidar cloud detection accuracy.
problem Segmenting lidar imagery into cloud locations.
method Semi-supervised learning with pre-training and fully supervised learning.
result FCN achieves higher cloud identification accuracy.
New theory allows simultaneous block-diagonalization of commuting operator fields.
problem Normal forms of operator fields.
method Generalized Nijenhuis torsions and generalized Haantjes algebra.
result Simultaneous block-diagonalization of commuting operator fields.
Posterior regularization enhances Bayesian hierarchical mixture clustering by improving node separation.
problem High nodal variance in BHMC trees, leading to weak separation between nodes at higher levels.
method Employing Posterior Regularization to impose max-margin constraints on nodes at every level.
result Improves cluster separation in BHMC models, enhancing overall model performance.
A new algorithm identifies features in non-stationary time series data.
problem Detecting features in non-stationary time series data.
method Hierarchical feature extraction using switching observable Markov chain models.
result The algorithm identifies features with high accuracy even under noisy conditions.
The paper calculates dimensions of higher Landau levels on compact manifolds.
problem Understanding Landau levels on compact manifolds in the large magnetic field limit.
method Computing dimensions as Riemann-Roch numbers, studying Toeplitz algebras, and proving isomorphisms.
result Each Landau level is isomorphic to a quantization twisted by an auxiliary bundle.
HIRO learns complex behaviors from few interactions.
problem Developing efficient hierarchical reinforcement learning methods.
method HIRO uses off-policy experience and automatic goal learning to generalize and be sample-efficient.
result HIRO learns complex behaviors from a few million samples, equivalent to a few days of real-time interaction.
SFBoW provides sentence embeddings with predefined dimensions.
problem Sentence embeddings problem at document-level.
method Refinement of Fuzzy Bag-of-Words, predefined dimension.
result Competitive performances in Semantic Textual Similarity benchmarks.
Improved image reconstruction and anomaly detection using hierarchical VAEs.
problem VAEs struggle with sharp images and high-level features.
method Added a new branch to hierarchical VAEs to separate high-level and low-level features.
result Results in sharper images and better anomaly detection.
New insights into binary perceptron reveal phase transitions and algorithmic thresholds.
problem Understanding the statistical-computational gap in binary perceptron models.
method Application of fully lifted random duality theory (fl RDT) to uncover structural changes.
result Numerical estimates of constraint density thresholds align with theoretical predictions.
Efficient graph-based algorithm for learning from bagged data.
problem Learning from bagged data with label proportions.
method Graph-based algorithm encouraging local smoothness and exploiting global structure.
result Preserves the mass of each bag while recovering true labels.
New brackets generalize Haantjes moduli and ensure integrability of operators.
problem Characterizing and integrating operators using Haantjes moduli.
method Introducing a new infinite class of brackets and proving integrability conditions.
result Vanishing of higher-level Nijenhuis torsions ensures integrability and block-diagonal form.
Proposes deep feature selection for HTN risk factors in African-Americans.
problem Identifying significant risk factors for heart damage in African-Americans with hypertension.
method Uses stacked auto-encoders for feature learning and representation in deep architecture.
result Deep learning approach leads to better results in identifying LVMI risk factors.
Geometric approach to PDEs using contact manifolds and Lagrangian Grassmannians.
problem Scalar PDEs in n variables of order one and two.
method Underlying (2n+1)-dimensional contact manifold and Lagrangian Grassmannian bundle.
result Introduction of geometric methods to PDEs, including scalar PDEs of order one and two.