Search Results for author:
Found 66 papers, 18 papers with code
Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks
However, the complexity of jet assignment increases when simultaneously considering both $H\rightarrow b\bar{b}$ reconstruction possibilities, i. e., two "resolved" small-radius jets each containing a shower initiated by a $b$-quark or one "boosted" large-radius jet containing a merged shower initiated by a $b\bar{b}$ pair.
Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions
Training in the presence of visual distractions is particularly difficult due to the high variation they introduce to representation learning.
Realizable Continuous-Space Shields for Safe Reinforcement Learning
For real-world robotic domains, it is essential to define safety specifications over continuous state and action spaces to accurately account for system dynamics and compute new actions that minimally deviate from the agent's original decision.
A Theory of Synaptic Neural Balance: From Local to Global Order
However, gradient descent on the regularized error function ought to converge to a balanced state, and thus network balance can be used to assess learning progress.
Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions.
Neural Erosion: Emulating Controlled Neurodegeneration and Aging in AI Systems
Creating controlled methods to simulate neurodegeneration in artificial intelligence (AI) is crucial for applications that emulate brain function decline and cognitive disorders.
Unraveling the Molecular Magic: AI Insights on the Formation of Extraordinarily Stretchable Hydrogels
The deliberate manipulation of ammonium persulfate, methylenebisacrylamide, dimethyleacrylamide, and polyethylene oxide concentrations resulted in the development of a hydrogel with an exceptional stretchability, capable of extending up to 260 times its original length.
AttentionStitch: How Attention Solves the Speech Editing Problem
In addition to speech generation, speech editing is also a crucial task, which requires the seamless and unnoticeable integration of edited speech into synthesized speech.
Evaluating the Performance of Large Language Models for Spanish Language in Undergraduate Admissions Exams
This study evaluates the performance of large language models, specifically GPT-3. 5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico.
Machine Learning-Enhanced Prediction of Surface Smoothness for Inertial Confinement Fusion Target Polishing Using Limited Data
In Inertial Confinement Fusion (ICF) process, roughly a 2mm spherical shell made of high density carbon is used as target for laser beams, which compress and heat it to energy levels needed for high fusion yield.
Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
We explore the performance of the extended capability of SPA-NET in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson.
Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors
Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities.
ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation
As an extension of the ClimSim dataset (Yu et al., 2024), we present ClimSim-Online, which also includes an end-to-end workflow for developing hybrid ML-physics simulators.
Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation
Generation of simulated detector response to collision products is crucial to data analysis in particle physics, but computationally very expensive.
Language Models can Solve Computer Tasks
We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function.
Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers
TransformerCVN classifies events with 90\% accuracy and improves the reconstruction of individual particles by 6\% over baseline methods which lack the integrated architecture of TransformerCVN.
Geometry-aware Autoregressive Models for Calorimeter Shower Simulations
Calorimeter shower simulations are often the bottleneck in simulation time for particle physics detectors.
Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments
In this paper, we propose Feasible Adversarial Robust RL (FARR), a novel problem formulation and objective for automatically determining the set of environment parameter values over which to be robust.
Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games
Instead of adding only deterministic best responses to the opponent's least exploitable population mixture, SP-PSRO also learns an approximately optimal stochastic policy and adds it to the population as well.
Deep Learning Models of the Discrete Component of the Galactic Interstellar Gamma-Ray Emission
A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky.
The Quarks of Attention
The gating mechanisms correspond to multiplicative extensions of the standard model and are used across all current attention-based deep learning architectures.
Anytime PSRO for Two-Player Zero-Sum Games
PSRO is based on the tabular double oracle (DO) method, an algorithm that is guaranteed to converge to a Nash equilibrium, but may increase exploitability from one iteration to the next.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation
To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data.
Tourbillon: a Physically Plausible Neural Architecture
The circular autoencoders are trained in self-supervised mode by recirculation algorithms and the top layer in supervised mode by stochastic gradient descent, with the option of propagating error information through the entire stack using non-symmetric connections.
SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics.
Improving Social Welfare While Preserving Autonomy via a Pareto Mediator
Machine learning algorithms often make decisions on behalf of agents with varied and sometimes conflicting interests.
Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity
There is a lack of scalable quantitative measures of reactivity for functional groups in organic chemistry.
XDO: A Double Oracle Algorithm for Extensive-Form Games
NXDO is the first deep RL method that can find an approximate Nash equilibrium in high-dimensional continuous-action sequential games.
A theory of capacity and sparse neural encoding
Motivated by biological considerations, we study sparse neural maps from an input layer to a target layer with sparse activity, and specifically the problem of storing $K$ input-target associations $(x, y)$, or memories, when the target vectors $y$ are sparse.
A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
We use Q* search to solve the Rubik's cube when formulated with a large action space that includes 1872 meta-actions and find that this 157-fold increase in the size of the action space incurs less than a 4-fold increase in computation time and less than a 3-fold increase in number of nodes generated when performing Q* search.
Detecting Pulmonary Coccidioidomycosis (Valley fever) with Deep Convolutional Neural Networks
We also use the classification model to identify regions of interest and localize the disease in the radiographic images, as illustrated through visual heatmaps.
How to GAN Higher Jet Resolution
QCD-jets at the LHC are described by simple physics principles.
Super-Resolution
High Energy Physics - Phenomenology
Deep-Learning-Based Kinematic Reconstruction for DUNE
To precisely reconstruct these kinematic characteristics of detected interactions at DUNE, we have developed and will present two CNN-based methods, 2-D and 3-D, for the reconstruction of final state particle direction and energy, as well as neutrino energy.
Deep machine learning-assisted multiphoton microscopy to reduce light exposure and expedite imaging
The skin dataset includes 550 images for each of the resolution levels.
Learning to Identify Electrons
We investigate whether state-of-the-art classification features commonly used to distinguish electrons from jet backgrounds in collider experiments are overlooking valuable information.
Data Analysis, Statistics and Probability High Energy Physics - Experiment High Energy Physics - Phenomenology
Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
Top quarks, produced in large numbers at the Large Hadron Collider, have a complex detector signature and require special reconstruction techniques.
Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning
Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds.
SPLASH: Learnable Activation Functions for Improving Accuracy and Adversarial Robustness
Furthermore, we show that SPLASH units significantly increase the robustness of deep neural networks to adversarial attacks.
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games
We also introduce an open-source environment for Barrage Stratego, a variant of Stratego with an approximate game tree complexity of $10^{50}$.
Sherpa: Robust Hyperparameter Optimization for Machine Learning
Sherpa is a hyperparameter optimization library for machine learning models.
Continuous Representation of Molecules Using Graph Variational Autoencoder
In order to continuously represent molecules, we propose a generative model in the form of a VAE which is operating on the 2D-graph structure of molecules.
A Fortran-Keras Deep Learning Bridge for Scientific Computing
Implementing artificial neural networks is commonly achieved via high-level programming languages like Python and easy-to-use deep learning libraries like Keras.
ColosseumRL: A Framework for Multiagent Reinforcement Learning in $N$-Player Games
Much of recent success in multiagent reinforcement learning has been in two-player zero-sum games.
Multiagent Systems
Symmetric-APL Activations: Training Insights and Robustness to Adversarial Attacks
Finally, we show that the use of Symmetric-APL activations can significantly increase the robustness of deep neural networks to adversarial attacks.
Learning in the Machine: To Share or Not to Share?
Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes.
Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints.
Computational Physics Atmospheric and Oceanic Physics
Curiosity-Driven Multi-Criteria Hindsight Experience Replay
Dealing with sparse rewards is a longstanding challenge in reinforcement learning.
Neural Network Regression with Beta, Dirichlet, and Dirichlet-Multinomial Outputs
We show that each target can be modeled as a sample from a Dirichlet distribution, where the parameters of the Dirichlet are provided by the output of a neural network, and that the combined model can be trained using the gradient of the data likelihood.
Solving the Rubik's Cube with Approximate Policy Iteration
Autodidactic Iteration is able to learn how to solve the Rubik’s Cube and the 15-puzzle without relying on human data.
The capacity of feedforward neural networks
Here we define the capacity of an architecture by the binary logarithm of the number of functions it can compute, as the synaptic weights are varied.
On Neuronal Capacity
We define the capacity of a learning machine to be the logarithm of the number (or volume) of the functions it can implement.
Gaussian Process Accelerated Feldman-Cousins Approach for Physical Parameter Inference
The unified approach of Feldman and Cousins allows for exact statistical inference of small signals that commonly arise in high energy physics.
Solving the Rubik's Cube Without Human Knowledge
A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision.
Learning in the Machine: the Symmetries of the Deep Learning Channel
Specifically, random backpropagation and its variations can be performed with the same non-linear neurons used in the main input-output forward channel, and the connections in the learning channel can be adapted using the same algorithm used in the forward channel, removing the need for any specialized hardware in the learning channel.
Efficient Antihydrogen Detection in Antimatter Physics by Deep Learning
Antihydrogen is at the forefront of antimatter research at the CERN Antiproton Decelerator.
Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass.
Learning in the Machine: Random Backpropagation and the Deep Learning Channel
It is remarkable both because of its effectiveness, in spite of using random matrices to communicate error information, and because it completely removes the taxing requirement of maintaining symmetric weights in a physical neural system.
Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks
Experiments in particle physics produce enormous quantities of data that must be analyzed and interpreted by teams of physicists.
Parameterized Machine Learning for High-Energy Physics
We investigate a new structure for machine learning classifiers applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
A Theory of Local Learning, the Learning Channel, and the Optimality of Backpropagation
The nature of the communicated information about the targets and the structure of the learning channel partition the space of learning algorithms.
Learning Activation Functions to Improve Deep Neural Networks
Artificial neural networks typically have a fixed, non-linear activation function at each neuron.
Ranked #176 on
Image Classification
on CIFAR-100
(using extra training data)
Searching for Higgs Boson Decay Modes with Deep Learning
Particle colliders enable us to probe the fundamental nature of matter by observing exotic particles produced by high-energy collisions.
Enhanced Higgs to $τ^+τ^-$ Searches with Deep Learning
The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the statistical power to cross the traditional 5$\sigma$ significance barrier without more data.
Searching for Exotic Particles in High-Energy Physics with Deep Learning
Standard approaches have relied on `shallow' machine learning models that have a limited capacity to learn complex non-linear functions of the inputs, and rely on a pain-staking search through manually constructed non-linear features.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Understanding Dropout
Dropout is a relatively new algorithm for training neural networks which relies on stochastically dropping out'' neurons during training in order to avoid the co-adaptation of feature detectors.
Complex-Valued Autoencoders
The general framework described here is useful to classify autoencoders and identify general common properties that ought to be investigated for each class, illuminating some of the connections between information theory, unsupervised learning, clustering, Hebbian learning, and autoencoders.
