AIMC Topic: Stochastic Processes

Clear Filters Showing 231 to 240 of 251 articles

Stochastic Gradient Descent Introduces an Effective Landscape-Dependent Regularization Favoring Flat Solutions.

Physical review letters Jun 9, 2023
Generalization is one of the most important problems in deep learning, where there exist many low-loss solutions due to overparametrization. Previous empirical studies showed a strong correlation between flatness of the loss landscape at a solution a...
Neural Networks, Computer Algorithms Stochastic Processes
View on PubMed DOI

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training.

Proceedings of the National Academy of Sciences of the United States of America Oct 26, 2021
In this paper, we introduce the , a nonconvex, yet analytically tractable, optimization program, in a quest to better understand deep neural networks that are trained for a sufficiently long time. As the name suggests, this model is derived by isolat...
Neural Networks, Computer Databases, Factual Deep Learning Humans Nonlinear Dynamics Stochastic Processes Computer Heuristics
View on PubMed DOI

Finite-time stability and optimal control of an impulsive stochastic reaction-diffusion vegetation-water system driven by Lévy process with time-varying delay.

Mathematical biosciences and engineering : MBE Sep 27, 2021
In this paper, a reaction-diffusion vegetation-water system with time-varying delay, impulse and Lévy jump is proposed. The existence and uniqueness of the positive solution are proved. Meanwhile, mainly through the principle of comparison, we obtain...
Diffusion Stochastic Processes Neural Networks, Computer Water Time Factors
View on PubMed DOI

New role for circuit expansion for learning in neural networks.

Physical review. E Feb 1, 2021
Many sensory pathways in the brain include sparsely active populations of neurons downstream from the input stimuli. The biological purpose of this expanded structure is unclear, but it may be beneficial due to the increased expressive power of the n...
Learning Neural Networks, Computer Models, Neurological Stochastic Processes
View on PubMed DOI

Learning dynamical systems in noise using convolutional neural networks.

Chaos (Woodbury, N.Y.) Oct 1, 2020
The problem of distinguishing deterministic chaos from non-chaotic dynamics has been an area of active research in time series analysis. Since noise contamination is unavoidable, it renders deterministic chaotic dynamics corrupted by noise to appear ...
Reproducibility of Results Deep Learning Nonlinear Dynamics Image Processing, Computer-Assisted Stochastic Processes Regression Analysis
View on PubMed DOI

Mantis-ml: Disease-Agnostic Gene Prioritization from High-Throughput Genomic Screens by Stochastic Semi-supervised Learning.

American journal of human genetics May 7, 2020
Access to large-scale genomics datasets has increased the utility of hypothesis-free genome-wide analyses. However, gene signals are often insufficiently powered to reach experiment-wide significance, triggering a process of laborious triaging of gen...
Disease Models, Animal Area Under Curve Epilepsy Genomics Genetic Association Studies Renal Insufficiency, Chronic Exome Amyotrophic Lateral Sclerosis Supervised Machine Learning Stochastic Processes Neural Networks, Computer Reproducibility of Results Animals Deep Learning ROC Curve Mice Humans
View on PubMed DOI

Bayesian framework for simulation of dynamical systems from multidimensional data using recurrent neural network.

Chaos (Woodbury, N.Y.) Dec 1, 2019
We suggest a new method for building data-driven dynamical models from observed multidimensional time series. The method is based on a recurrent neural network with specific structure, which allows for the joint reconstruction of both a low-dimension...
Stochastic Processes Atmosphere Signal Processing, Computer-Assisted Probability Neural Networks, Computer Data Analysis Algorithms Computer Simulation Models, Theoretical Bayes Theorem
View on PubMed DOI

Machine-Learning and Stochastic Tumor Growth Models for Predicting Outcomes in Patients With Advanced Non-Small-Cell Lung Cancer.

JCO clinical cancer informatics Sep 1, 2019
PURPOSE: The prediction of clinical outcomes for patients with cancer is central to precision medicine and the design of clinical trials. We developed and validated machine-learning models for three important clinical end points in patients with adva...
Lung Neoplasms Treatment Outcome Carcinoma, Non-Small-Cell Lung Randomized Controlled Trials as Topic Neoplasm Staging Molecular Targeted Therapy Machine Learning Combined Modality Therapy Models, Biological Kaplan-Meier Estimate Algorithms Stochastic Processes Tumor Burden Prognosis Neoplasm Metastasis Humans
View on PubMed DOI

Artificial intelligence in drug combination therapy.

Briefings in bioinformatics Jul 19, 2019
Currently, the development of medicines for complex diseases requires the development of combination drug therapies. It is necessary because in many cases, one drug cannot target all necessary points of intervention. For example, in cancer therapy, a...
Logistic Models Stochastic Processes Humans Gene Expression Regulation, Neoplastic Expert Systems Support Vector Machine Neural Networks, Computer Neoplasms Bayes Theorem Drug Therapy, Combination Artificial Intelligence Least-Squares Analysis Deep Learning Drug Resistance Machine Learning Computational Biology Drug Interactions
View on PubMed DOI

A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: from mitigation to exploitation.

Faraday discussions Feb 18, 2019
Memristive devices represent a promising technology for building neuromorphic electronic systems. In addition to their compactness and non-volatility, they are characterized by their computationally relevant physical properties, such as their state-d...
Computer Simulation Neural Networks, Computer Information Storage and Retrieval Equipment Design Algorithms Stochastic Processes Electronics
View on PubMed DOI
Popular Topics
Recent Journals