AIMC Topic: Learning

Clear Filters Showing 1011 to 1020 of 1476 articles

Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning.

Neural computation
Humans are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed , is one of the major r...

Neural Classification of Compost Maturity by Means of the Artificial Neural Network and Algorithm.

International journal of environmental research and public health
neural models and the algorithm were used to produce a classifier identifying the quality classes of compost, according to the degree of its maturation within a period of time recorded in digital images. Digital images of compost at different stage...

An approach on the implementation of full batch, online and mini-batch learning on a Mamdani based neuro-fuzzy system with center-of-sets defuzzification: Analysis and evaluation about its functionality, performance, and behavior.

PloS one
Due to the rapid technological evolution and communications accessibility, data generated from different sources of information show an exponential growth behavior. That is, volume of data samples that need to be analyzed are getting larger, so the m...

Multiclass heterogeneous domain adaptation via bidirectional ECOC projection.

Neural networks : the official journal of the International Neural Network Society
Heterogeneous domain adaptation aims to exploit the source domain data to train a prediction model for the target domain with different input feature space. Current methods either map the data points from different domains with different feature spac...

A critique of pure learning and what artificial neural networks can learn from animal brains.

Nature communications
Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better supervised learning algorithms. However, in stark contrast to young animals (including humans), training such networks requires enormous numbers of labeled examples, l...

A two-route CNN model for bank account classification with heterogeneous data.

PloS one
Classifying bank accounts by using transaction data is encouraging in cracking down on illegal financial activities. However, few research simultaneously use heterogenous features, which are embedded in the time series data. In this paper, a two rout...

Personalised modelling with spiking neural networks integrating temporal and static information.

Neural networks : the official journal of the International Neural Network Society
This paper proposes a new personalised prognostic/diagnostic system that supports classification, prediction and pattern recognition when both static and dynamic/spatiotemporal features are presented in a dataset. The system is based on a proposed cl...

Assisted therapeutic system based on reinforcement learning for children with autism.

Computer assisted surgery (Abingdon, England)
Assisted therapy is increasingly used in autism spectrum disorders (ASD) for improving social interaction and communication skills in recent years. A lot of studies have proven that the form of interactive games for therapy has a good effect on child...

Beyond the "Conceptual Nervous System": Can computational cognitive neuroscience transform learning theory?

Behavioural processes
In the last century, learning theory has been dominated by an approach assuming that associations between hypothetical representational nodes can support the acquisition of knowledge about the environment. The similarities between this approach and c...

A programmable neural virtual machine based on a fast store-erase learning rule.

Neural networks : the official journal of the International Neural Network Society
We present a neural architecture that uses a novel local learning rule to represent and execute arbitrary, symbolic programs written in a conventional assembly-like language. This Neural Virtual Machine (NVM) is purely neurocomputational but supports...