Hopfield networks improve reaction template prediction for few/zero-shot scenarios.
problem Predicting reaction templates for new molecules in CASP.
method Adapted Hopfield networks to associate reaction templates, molecules, and structural information.
result Significantly improved performance for templates with few or zero training examples.
Generative adversarial network creates motion templates for agent training.
problem Training reinforcement learning agents with meaningful behaviors.
method Trains a GAN to produce motion templates from raw pixel data.
result Generated motions enable training reinforcement learning agents in novel environments.
SrvfNet aligns multiple functional data to templates without supervision.
problem Aligning large collections of functional data to templates without labeled data.
method Generative deep learning framework using SRVF and fully-connected layers.
result Framework achieves alignment and optimal template prediction without supervision.
Generative models improve CECT template matching reliability.
problem Insufficient template matching for accurate CECT structure assessment.
method Image-derived generative adversarial network for pseudo-macromolecular structures.
result Statistical credibility of CECT template matching significantly improved.
DSPNs generalize SPNs for sequence data, inheriting tractable inference.
problem Inference on sequence data is often intractable.
method Dynamic Sum Product Networks (DSPNs) with a template network repeated for varying lengths.
result DSPNs inherit linear inference complexity from SPNs, unlike DBNs which are exponential.
MAGIC generates image collages from set templates using attention and set representations.
problem Generating image collages from set templates is challenging for classical models.
method Memory Attentive Generation of Image Collages (MAGIC) using Set-Transformer layers and set-pooling.
result MAGIC can generate image collages from set templates in one forward pass.
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.
Templates are branched 2-manifolds with semi-flows used to model `chaotic' hyperbolic invariant sets of flows on 3-manifolds. Knotted orbits on a template correspond to those in the original flow. Birman and Williams conjectured that for any given template the number of prime factors of the knots realized would be boun…
A new method for tracking objects using diverse templates.
problem Improving visual tracking performance and robustness.
method Proposes a framework that uses additional object templates and a new diversity measure in siamese feature space.
result Achieves strong empirical results on tracking benchmarks, improving performance and robustness.
A new method predicts organic reactions faster and more accurately.
problem Predicting reaction outcomes in complex molecules is computationally challenging.
method Identifies reaction centers, enumerates candidate products, and scores them using a Weisfeiler-Lehman Difference Network.
result Framework outperforms template-based methods with a 10% margin and runs faster.
METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.
problem Predicting possible reaction substrates for complex molecules from simpler precursors.
method METRO (Molecule-Edit Templates for RetrOsynthesis) uses minimal templates to predict reactions efficiently and accurately.
result METRO achieves state-of-the-art results on standard benchmarks, reducing computational overhead.
New insights into Lorenz and Rössler links, showing they are distinct.
problem Comparing Lorenz and Rössler links and understanding their differences.
method Analyzing periodic orbits and templates of the Lorenz, horseshoe, and Rössler systems.
result Found infinite families of links that can be embedded in both templates, but also constructed examples of Lorenz links that are not horseshoe or Rössler.
Geometric framework explains deep learning performance.
problem Understanding why deep learning works well across various tasks.
method Comparing deep learning to quantum computations and diffeomorphic template matching.
result Geometric structures of different deep learning systems.
New graph learning framework outperforms existing methods.
problem Learning effective representations of large graphs with high degree variability.
method Deep hierarchical decompositions and neural network template unrolling over the hierarchy.
result Empirically outperforms state-of-the-art graph classification methods on large social network datasets.
New method to classify simple Smale flows on S3.
problem Classifying simple Smale flows on S3. method Embedded template and Kauffman's invariant of spatial graphs.
result Isotopic classification of simple Smale flows on S3. Dasgupta and Shulman showed that a two-round variant of the EM algorithm can learn mixture of Gaussian distributions with near optimal precision with high probability if the Gaussian distributions are well separated and if the dimension is sufficiently high. In this paper, we generalize their theory to learning mixture…
We describe the Williams zeta functions and the twist zeta functions of sub-Lorenz templates generated by renormalizable Lorenz maps, in terms of the corresponding zeta-functions of the sub-Lorenz templates generated by the renormalized map and by the map that determines the renormalization type.
Graph clustering method uses templates to match vertices and outperforms classical methods.
problem Graph clustering with additional structural information.
method Formulates graph clustering as template matching, using orthonormal matrices for embedding.
result Method outperforms classical methods, especially for challenging cases.
A flexible machine learning model infers the morphology of the Galactic Center Excess.
problem Inferring the unknown morphology of the Galactic Center Excess using Fermi gamma-ray data.
method Used a Gaussian process (GP) to model the Galactic Center Excess (GCE) as a flexible, non-parametric machine learning model.
result The best-fit GP contains morphological features not typically associated with traditional GCE studies, such as a localized bright source and a diagonal arm.
We analyze and correct bias in template shape estimation using geometric statistics.
problem Asymptotic bias in template shape estimation.
method Tools from geometric statistics, stratified geometry of shape space, Taylor expansion, bootstrap procedures.
result Proposed methods to quantify and correct bias in template shape estimation.
Designs a Cellular Automata rule for forming touching loop patterns.
problem Forming stable touching loop patterns in a 2D grid.
method Developed a Cellular Automata rule that uses templates to cover the space and match patterns.
result The rule successfully evolves stable touching loop patterns in a 2D grid.
The fact that the modular template coincides with the Lorenz template, discovered by Ghys, implies modular knots have very peculiar properties. We obtain a generalization of these results to other Hecke triangle groups. In this context, the geodesic flow can never be seen as a flow on a subset of S3, and one is led …
Paper addresses data reconstruction from privacy-protected templates using STCA.
problem Reconstructing privacy-sensitive data from protected templates.
method Sparse ternary coding with ambiguization (STCA) for privacy preservation.
result STCA maintains theoretical performance against deep reconstruction attacks for synthetic data but requires special measures for real images.
TentacleNet improves binarized CNNs, reducing accuracy loss and memory usage.
problem Excessive accuracy loss in binarized CNNs.
method Parallelization inspired by ensemble learning theory, end-to-end trainable compact topology.
result Significant memory savings compared to state-of-the-art binary ensemble methods.
X-DC improves speech separation by making DNNs more interpretable.
problem Black-box nature of DNNs in speech separation tasks.
method Introduces X-DC, a DNN architecture that interprets as spectrogram template fitting followed by Wiener filtering.
result X-DC achieves comparable speech separation performance to DC but with enhanced interpretability.
GPCDL uses Gaussian Processes to learn smooth templates from data.
problem Lack of smoothness in learned templates leads to overfitting and poor predictive performance.
method GPCDL incorporates Gaussian Process priors to enforce smoothness in the learned templates.
result GPCDL outperforms unregularized CDL in accuracy and predictive performance across various SNRs and applications.
Paper tackles curve pattern identification from fragmented cultural heritage objects.
problem Identify full design of curve patterns from fragmented cultural heritage objects.
method Two-stage matching algorithm combining template matching and CNN re-ranking.
result Proposed algorithm outperforms traditional methods in identifying curve patterns from fragmented objects.
New model predicts chemical reactions with conditional graph logic networks.
problem Predicting chemical reactions for synthesizing molecules.
method Conditional Graph Logic Network (CGLN) based on graph neural networks.
result Significant improvement of 8.1% over state-of-the-art methods.
Paper introduces template functions for featurizing persistence diagrams.
problem Featurizing persistence diagrams for machine learning.
method Characterizes compactness, constructs dense subsets of continuous functions.
result Template functions enable supervised learning with persistence diagrams.
G2Gs transforms target molecules into reactants without templates, improving accuracy.
problem Predicting retrosynthesis from target molecules efficiently and accurately.
method Transforming target molecular graphs into reactant graphs via variational graph translation.
result G2Gs achieves top-1 accuracy close to state-of-the-art template-based methods.
A deep learning approach generates math word problems in multiple languages.
problem Template-based mechanisms for generating mathematical word problems lack customizability and creativity.
method Character Level Long Short Term Memory Network (LSTM) and POS tags are used to generate and resolve constraints in generated problems.
result The approach generates accurate math word problems in English and Sinhala with over 90% accuracy.
A hybrid CNN with shared parameters learns to incorporate recurrent structures.
problem Designing efficient recurrent neural networks.
method Parameter sharing scheme combining CNN and recurrent layers.
result Substantial parameter savings with competitive accuracy.
Adaptive template systems improve feature extraction from persistence diagrams for machine learning.
problem Feature extraction from persistence diagrams for machine learning.
method Adaptive template systems using CDER, GMM, and HDBSCAN algorithms.
result Adaptive template systems yield competitive and often superior results in classification tasks.
Method finds multiple noisy graph templates in large graphs.
problem Finding multiple graph templates in noisy large graphs.
method Iteratively penalizes node-pair similarity matrix in matched filter algorithm.
result Method can sequentially discover multiple templates under mild model conditions.
A new matrix factorization method that approximates data without requiring nonnegativity or convexity.
problem Approximating data matrices without the constraints of nonnegativity or convexity.
method A multi-objective optimization problem finds conical combinations of templates that approximate a given data matrix.
result The method allows for approximation of data sets without the usual constraints of nonnegativity or convexity.
Study shows how transformers classify symbols without naming them, proving a margin-versus-collision criterion.
problem How transformers classify symbols without naming them.
method Logistic classification analysis of transformer-kernel regime, colored collision graph.
result Decomposes learned predictor into ideal template-level classifier and finite-sample perturbation.
The paper proposes a deep learning technique for structured and composable representations.
problem Learning structured and composable representations from input images and discrete labels.
method End-to-end deep learning to learn representations based on distance estimates between class label and contextual information.
result The representations have a clear structure allowing for class and environment decomposition.
Robust visual tracking for long video sequences is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor, as this descriptor is robust to problems such as p…
A new protocol corrects confounding effects to measure alignment-induced activation shifts accurately.
problem Confounding effects in measuring alignment-induced activation shifts using naive methods.
method Introduces a four-variant decomposition to separate alignment shift from template effects.
result Correctly measures alignment-induced activation shifts, recovering behaviorally active subspace.
Models learn spatial templates from implicit language, predicting spatial arrangements with high accuracy.
problem Predicting spatial arrangements from implicit spatial language.
method Simple neural-based models leveraging annotated images and structured text.
result Models can predict spatial arrangements from implicit spatial language with high accuracy, even for unseen objects.
We construct a template with two ribbons that describes the topology of all periodic orbits of the geodesic flow on the unit tangent bundle to any sphere with three cone points with hyperbolic metric. The construction relies on the existence of a particular coding with two letters for the geodesics on these orbifolds.
Hides the complexity of neural networks, making them more transparent.
problem Lack of transparency in Neural Networks hinders their adoption.
method Proposes Hide-and-Seek (HnS) framework for training interpretable neural networks.
result Interpretable neural networks can be trained without sacrificing predictive power.
Framework uses expert intervention to solve long-horizon reinforcement learning tasks.
problem Long horizon robot learning tasks with sparse rewards.
method Option templates and expert intervention to enable high-level task understanding.
result Framework outperforms state-of-the-art approaches by two orders of magnitude.
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.
Paper simplifies link classification in 3-sphere using braids and templates.
problem Classify links in the 3-sphere.
method Simplified braid description, generalised T-links, bunch algorithm.
result Established upper volume bound for 3-manifolds.
Choose any oriented link type X and closed braid representatives X[+], X[-] of X, where X[-] has minimal braid index among all closed braid representatives of X. The main result of this paper is a `Markov theorem without stabilization'. It asserts that there is a complexity function and a finite set of `templates' such…
Enhanced detection of sneutrinos at the LHC using machine learning.
problem Detecting rare new physics signals in the presence of significant backgrounds.
method Machine learning models (XGBoost and deep neural network) applied to template fit analysis.
result Template fit outperforms simple cuts in enhancing sneutrino detectability.
TempLe learns transition templates for efficient multi-task RL.
problem Efficiently transferring knowledge across different RL tasks with varying state/action spaces.
method Generates transition dynamics templates to abstract similarities between tasks.
result Achieves significantly lower sample complexity than single-task or multi-task methods.