arXiv subjects

Janet Wiles

Publications and source records attributed to Janet Wiles.

5 recordsLinked to original sources

arXiv2024

Socially Minded Intelligence: How Individuals, Groups, and Artificial Intelligence Can Make Each Other Smarter (or Not)

A core part of human intelligence is the ability to work flexibly with others to achieve goals. The incorporation of artificial agents into human spaces is making increasing demands on artificial intelligence (AI) to demonstrate and facilitate this ability. However, this kind of flexibility is not well understood because existing approaches to intelligence typically construe this either as an individual-difference trait or as a property of groups. We argue that by focusing either on individual or collective intelligence without considering their dynamic interaction, existing conceptualizations of intelligence limit the potential of people and AI systems. To address this impasse, we propose a new kind of intelligence, 'socially minded intelligence', that can be applied to both individuals and collectives. We outline how socially minded intelligence might be measured and cultivated within people, how it might be modelled in AI agents, and how it might be applied to other intelligent systems.

cs.HC↗

arXiv2021

User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis

This paper reports on progress integrating the speech recognition toolkit ESPnet into Elpis, a web front-end originally designed to provide access to the Kaldi automatic speech recognition toolkit. The goal of this work is to make end-to-end speech recognition models available to language workers via a user-friendly graphical interface. Encouraging results are reported on (i) development of an ESPnet recipe for use in Elpis, with preliminary results on data sets previously used for training acoustic models with the Persephone toolkit along with a new data set that had not previously been used in speech recognition, and (ii) incorporating ESPnet into Elpis along with UI enhancements and a CUDA-supported Dockerfile.

cs.CL↗

arXiv2018

Determining the Number of Samples Required to Estimate Entropy in Natural Sequences

Calculating the Shannon entropy for symbolic sequences has been widely considered in many fields. For descriptive statistical problems such as estimating the N-gram entropy of English language text, a common approach is to use as much data as possible to obtain progressively more accurate estimates. However in some instances, only short sequences may be available. This gives rise to the question of how many samples are needed to compute entropy. In this paper, we examine this problem and propose a method for estimating the number of samples required to compute Shannon entropy for a set of ranked symbolic natural events. The result is developed using a modified Zipf-Mandelbrot law and the Dvoretzky-Kiefer-Wolfowitz inequality, and we propose an algorithm which yields an estimate for the minimum number of samples required to obtain an estimate of entropy with a given confidence level and degree of accuracy.

cs.IT↗

arXiv2018

Fast Entropy Estimation for Natural Sequences

It is well known that to estimate the Shannon entropy for symbolic sequences accurately requires a large number of samples. When some aspects of the data are known it is plausible to attempt to use this to more efficiently compute entropy. A number of methods having various assumptions have been proposed which can be used to calculate entropy for small sample sizes. In this paper, we examine this problem and propose a method for estimating the Shannon entropy for a set of ranked symbolic natural events. Using a modified Zipf-Mandelbrot-Li law and a new rank-based coincidence counting method, we propose an efficient algorithm which enables the entropy to be estimated with surprising accuracy using only a small number of samples. The algorithm is tested on some natural sequences and shown to yield accurate results with very small amounts of data.

physics.data-an↗

arXiv2015

Spike Event Based Learning in Neural Networks

A scheme is derived for learning connectivity in spiking neural networks. The scheme learns instantaneous firing rates that are conditional on the activity in other parts of the network. The scheme is independent of the choice of neuron dynamics or activation function, and network architecture. It involves two simple, online, local learning rules that are applied only in response to occurrences of spike events. This scheme provides a direct method for transferring ideas between the fields of deep learning and computational neuroscience. This learning scheme is demonstrated using a layered feedforward spiking neural network trained self-supervised on a prediction and classification task for moving MNIST images collected using a Dynamic Vision Sensor.

cs.NE↗