Search Results for author:
Found 23 papers, 0 papers with code
Agile gesture recognition for low-power applications: customisation for generalisation
Automated hand gesture recognition has long been a focal point in the AI community.
Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees
A key technical focus of the work is in providing performance guarantees for these new AI correctors through bounds on the probabilities of incorrect decisions.
Relative intrinsic dimensionality is intrinsic to learning
High dimensional data can have a surprising property: pairs of data points may be easily separated from each other, or even from arbitrary subsets, with high probability using just simple linear classifiers.
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation.
How adversarial attacks can disrupt seemingly stable accurate classifiers
We introduce a simple generic and generalisable framework for which key behaviours observed in practical systems arise with high probability -- notably the simultaneous susceptibility of the (otherwise accurate) model to easily constructed adversarial attacks, and robustness to random perturbations of the input data.
Agile gesture recognition for capacitive sensing devices: adapting on-the-job
However, there is growing demand for gesture recognition technology that can be implemented on low-power devices using limited sensor data instead of high-dimensional inputs like hand images.
Towards a mathematical understanding of learning from few examples with nonlinear feature maps
We consider the problem of data classification where the training set consists of just a few data points.
Learning from few examples with nonlinear feature maps
In this work we consider the problem of data classification in post-classical settings were the number of training examples consists of mere few data points.
Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation
Recent work by Mellor et al (2021) showed that there may exist correlations between the accuracies of trained networks and the values of some easily computable measures defined on randomly initialised networks which may enable to search tens of thousands of neural architectures without training.
Situation-based memory in spiking neuron-astrocyte network
Three pools of stimuli patterns are considered: external patterns, patterns from the situation associative pool regularly presented to the network and learned by the network, and patterns already learned and remembered by astrocytes.
Learning from scarce information: using synthetic data to classify Roman fine ware pottery
To address the challenge we propose to use a transfer learning approach whereby the model is first trained on a synthetic dataset replicating features of the original objects.
High-dimensional separability for one- and few-shot learning
New stochastic separation theorems for data with fine-grained structure are formulated and proved.
The Feasibility and Inevitability of Stealth Attacks
Such a stealth attack could be conducted by a mischievous, corrupt or disgruntled member of a software development team.
Demystification of Few-shot and One-shot Learning
Few-shot and one-shot learning have been the subject of active and intensive research in recent years, with mounting evidence pointing to successful implementation and exploitation of few-shot learning algorithms in practice.
General stochastic separation theorems with optimal bounds
To manage errors and analyze vulnerabilities, the stochastic separation theorems should evaluate the probability that the dataset will be Fisher separable in given dimensionality and for a given class of distributions.
On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems
We show that in both cases, i. e., in the case of an attack based on adversarial examples and in the case of a stealth attack, the dimensionality of the AI's decision-making space is a major contributor to the AI's susceptibility.
High--Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality
High-dimensional data and high-dimensional representations of reality are inherent features of modern Artificial Intelligence systems and applications of machine learning.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Blessing of dimensionality at the edge
Another feature of this approach is that, in the supervised setting, the computational complexity of training is linear in the number of training samples.
Symphony of high-dimensional brain
This paper is the final part of the scientific discussion organised by the Journal "Physics of Life Rviews" about the simplicity revolution in neuroscience and AI.
Fast Construction of Correcting Ensembles for Legacy Artificial Intelligence Systems: Algorithms and a Case Study
This paper presents a technology for simple and computationally efficient improvements of a generic Artificial Intelligence (AI) system, including Multilayer and Deep Learning neural networks.
Augmented Artificial Intelligence: a Conceptual Framework
We combine some ideas of learning in heterogeneous multiagent systems with new and original mathematical approaches for non-iterative corrections of errors of legacy AI systems.
Knowledge Transfer Between Artificial Intelligence Systems
We consider the fundamental question: how a legacy "student" Artificial Intelligent (AI) system could learn from a legacy "teacher" AI system or a human expert without complete re-training and, most importantly, without requiring significant computational resources.
One-Trial Correction of Legacy AI Systems and Stochastic Separation Theorems
The tuning method that we propose enables dealing with errors without the need to re-train the system.
