AIMC Topic: Stochastic Processes

Clear Filters Showing 121 to 130 of 251 articles

Multi-task learning improves ancestral state reconstruction.

Theoretical population biology
We consider the ancestral state reconstruction problem where we need to infer phenotypes of ancestors using observations from present-day species. For this problem, we propose a multi-task learning method that uses regularized maximum likelihood to e...

Global Synchronization of Coupled Fractional-Order Recurrent Neural Networks.

IEEE transactions on neural networks and learning systems
This paper presents new theoretical results on the global synchronization of coupled fractional-order recurrent neural networks. Under the assumptions that the coupled fractional-order recurrent neural networks are sequentially connected in form of a...

qTorch: The quantum tensor contraction handler.

PloS one
Classical simulation of quantum computation is necessary for studying the numerical behavior of quantum algorithms, as there does not yet exist a large viable quantum computer on which to perform numerical tests. Tensor network (TN) contraction is an...

Ensemble Neural Networks (ENN): A gradient-free stochastic method.

Neural networks : the official journal of the International Neural Network Society
In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are calculated by the e...

Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks.

Neural networks : the official journal of the International Neural Network Society
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes...

STRAINet: Spatially Varying sTochastic Residual AdversarIal Networks for MRI Pelvic Organ Segmentation.

IEEE transactions on neural networks and learning systems
Accurate segmentation of pelvic organs is important for prostate radiation therapy. Modern radiation therapy starts to use a magnetic resonance image (MRI) as an alternative to computed tomography image because of its superior soft tissue contrast an...

MetScore: Site of Metabolism Prediction Beyond Cytochrome P450 Enzymes.

ChemMedChem
The metabolism of xenobiotics by humans and other organisms is a complex process involving numerous enzymes that catalyze phase I (functionalization) and phase II (conjugation) reactions. Herein we introduce MetScore, a machine learning model that ca...

Emergence of spontaneous assembly activity in developing neural networks without afferent input.

PLoS computational biology
Spontaneous activity is a fundamental characteristic of the developing nervous system. Intriguingly, it often takes the form of multiple structured assemblies of neurons. Such assemblies can form even in the absence of afferent input, for instance in...

Comparison of logistic regression, support vector machines, and deep learning classifiers for predicting memory encoding success using human intracranial EEG recordings.

Journal of neural engineering
OBJECTIVE: We sought to test the performance of three strategies for binary classification (logistic regression, support vector machines, and deep learning) for the problem of predicting successful episodic memory encoding using direct brain recordin...