José del R. Millán

Axel Uran, Coert van Gemeren, Rosanne van Diepen et al.

The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in neuroscience, lies in the complexity of the information that is processed, the availability of data and the cost of producing sufficient high quality annotations. Inspired by its application in computer vision, we introduce transfer learning on electrophysiological data to enable training a model with limited amounts of data. Our method was tested on the dataset of the BCI competition IV 2a and compared to the top results that were obtained using traditional machine learning techniques. Using our DL model we outperform the top result of the competition by 33%. We also explore transferability of knowledge between trained models over different experiments, called inter-experimental transfer learning. This reduces the amount of required data even further and is especially useful when few subjects are available. This method is able to outperform the standard deep learning methods used in the BCI competition IV 2b approaches by 18%. In this project we propose a method that can produce reliable electroencephalography (EEG) signal classification, based on modest amounts of training data through the use of transfer learning.

Michael Hersche, José del R. Millán, Luca Benini et al.

Key properties of brain-inspired hyperdimensional (HD) computing make it a prime candidate for energy-efficient and fast learning in biosignal processing. The main challenge is however to formulate embedding methods that map biosignal measures to a binary HD space. In this paper, we explore variety of such embedding methods and examine them with a challenging application of motor imagery brain-computer interface (MI-BCI) from electroencephalography (EEG) recordings. We explore embedding methods including random projections, quantization based thermometer and Gray coding, and learning HD representations using end-to-end training. All these methods, differing in complexity, aim to represent EEG signals in binary HD space, e.g. with 10,000 bits. This leads to development of a set of HD learning and classification methods that can be selectively chosen (or configured) based on accuracy and/or computational complexity requirements of a given task. We compare them with state-of-the-art linear support vector machine (SVM) on an NVIDIA TX2 board using the 4-class BCI competition IV-2a dataset as well as a new 3-class dataset. Compared to SVM, results on 3-class dataset show that simple thermometer embedding achieves moderate average accuracy (79.56% vs. 82.67%) with 26.8$\times$ faster training time and 22.3$\times$ lower energy; on the other hand, switching to end-to-end training with learned HD representations wipes out these training benefits while boosting the accuracy to 84.22% (1.55% higher than SVM). Similar trend is observed on the 4-class dataset where SVM achieves on average 74.29%: the thermometer embedding achieves 89.9$\times$ faster training time and 58.7$\times$ lower energy, but a lower accuracy (67.09%) than the learned representation of 72.54%.

Serafeim Perdikis, Robert Leeb, Ricardo Chavarriaga et al.

This work studies the class of algorithms for learning with side-information that emerge by extending generative models with embedded context-related variables. Using finite mixture models (FMM) as the prototypical Bayesian network, we show that maximum-likelihood estimation (MLE) of parameters through expectation-maximization (EM) improves over the regular unsupervised case and can approach the performances of supervised learning, despite the absence of any explicit ground truth data labeling. By direct application of the missing information principle (MIP), the algorithms' performances are proven to range between the conventional supervised and unsupervised MLE extremities proportionally to the information content of the contextual assistance provided. The acquired benefits regard higher estimation precision, smaller standard errors, faster convergence rates and improved classification accuracy or regression fitness shown in various scenarios, while also highlighting important properties and differences among the outlined situations. Applicability is showcased with three real-world unsupervised classification scenarios employing Gaussian Mixture Models. Importantly, we exemplify the natural extension of this methodology to any type of generative model by deriving an equivalent context-aware algorithm for variational autoencoders (VAs), thus broadening the spectrum of applicability to unsupervised deep learning with artificial neural networks. The latter is contrasted with a neural-symbolic algorithm exploiting side-information.