Analysis and visualization of sleep stages based on deep neural networks

Krauß, Patrick; Metzner, Claus; Joshi, Nidhi; Schulze, Holger; Traxdorf, Maximilian; Maier, Andreas; Schilling, Achim

doi:10.1016/j.nbscr.2021.100064

Cited by 35 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, it is not even necessary to record a large number of EEG channels. Indeed, we have shown that reliable sleep-stage detection is even possible based on a single channel 14 , thanks to the remarkable ability of machine learning systems to extract those features from the data that are most relevant for the classification task.…”

Section: Introductionmentioning

confidence: 99%

Sleep as a random walk: a super-statistical analysis of EEG data across sleep stages

et al. 2021

Self Cite

View full text Add to dashboard Cite

In clinical practice, human sleep is classified into stages, each associated with different levels of muscular activity and marked by characteristic patterns in the EEG signals. It is however unclear whether this subdivision into discrete stages with sharply defined boundaries is truly reflecting the dynamics of human sleep. To address this question, we consider one-channel EEG signals as heterogeneous random walks: stochastic processes controlled by hyper-parameters that are themselves time-dependent. We first demonstrate the heterogeneity of the random process by showing that each sleep stage has a characteristic distribution and temporal correlation function of the raw EEG signals. Next, we perform a super-statistical analysis by computing hyper-parameters, such as the standard deviation, kurtosis, and skewness of the raw signal distributions, within subsequent 30-second epochs. It turns out that also the hyper-parameters have characteristic, sleep-stage-dependent distributions, which can be exploited for a simple Bayesian sleep stage detection. Moreover, we find that the hyper-parameters are not piece-wise constant, as the traditional hypnograms would suggest, but show rising or falling trends within and across sleep stages, pointing to an underlying continuous rather than sub-divided process that controls human sleep. Based on the hyper-parameters, we finally perform a pairwise similarity analysis between the different sleep stages, using a quantitative measure for the separability of data clusters in multi-dimensional spaces.

show abstract

Section: Introductionmentioning

confidence: 99%

Sleep as a random walk: a super-statistical analysis of EEG data across sleep stages

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our integrated model of auditory (phantom) perception demonstrates that the fusion of computational neuroscience, AI, and experimental neuroscience leads to innovative ideas and paves the way for further advances in neuroscience and AI research. For instance, novel evaluation techniques for neurophysiological data based on AI and Bayesian statistics were recently established [156][157][158][159], the role of noise in neural networks and other biological information processing systems was considered in [160][161][162][163], and the benefit and application of noise and randomness in Machine Learning approaches was further investigated in [43,164,165]. On the one hand, the fusion of these complementary fields may evince the neural mechanisms of tinnitus (CCN, [63]) and information processing principles that underwrite functional brain architectures.…”

Section: Discussionmentioning

confidence: 99%

Predictive coding and stochastic resonance as fundamental principles of auditory perception

Schilling¹,

Sedley²,

Gerum³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Cognitive computational neuroscience (CCN) suggests that to gain a mechanistic understanding of brain function, hypothesis driven experiments should be accompanied by biologically plausible computational models. This novel research paradigm offers a way from alchemy to chemistry, in auditory neuroscience. With a special focus on tinnitus -as the prime example of auditory phantom perception -we review recent work at the intersection of artificial intelligence, psychology, and neuroscience, foregrounding the idea that experiments will yield mechanistic insight only when employed to test formal or computational models. This view challenges the popular notion that tinnitus research is primarily data limited, and that producing large, multi-modal, and complex data-sets, analyzed with advanced data analysis algorithms, will lead to fundamental insights into how tinnitus emerges. We conclude that two fundamental processing principles -being ubiquitous in the brain -best fit to a vast number of experimental results and therefore provide the most explanatory power: predictive coding as a top-down, and stochastic resonance as a complementary bottom-up mechanism. Furthermore, we argue that even though contemporary artificial intelligence and machine learning approaches largely lack biological plausibility, the models to be constructed will have to draw on concepts from these fields; since they provide a formal account of the requisite computations that underlie brain function. Nevertheless, biological fidelity will have to be addressed, allowing for testing possible treatment strategies in silico, before application in animal or patient studies. This iteration of computational and empirical studies may help to open the 'black boxes' of both machine learning and the human brain.

show abstract

“…A neural network implementation of hippocampal successor representations, especially, promises advances in both fields. Following the research agenda of Cognitive Computational Neuroscience proposed by Kriegeskorte et al [81], neuroscience and cognitive science benefit from such models by gaining deeper understanding of brain computations [50,82,83]. Conversely, for artificial intelligence and machine learning, neural network-based multi-scale successor representations to learn and process structural knowledge (as an example of neuroscience-inspired artificial intelligence [84]), might be a further step to overcome the limitations of contemporary deep learning [85][86][87][88] and towards human-level artificial general intelligence.…”

Section: Discussionmentioning

confidence: 99%

“…By color-coding each projected data point of a data set according to its label, the representation of the data can be visualized as a set of point clusters. For instance, MDS has already been applied to visualize for instance word class distributions of different linguistic corpora [48], hidden layer representations (embeddings) of artificial neural networks [49,50], structure and dynamics of recurrent neural networks [51][52][53], or brain activity patterns assessed during e.g. pure tone or speech perception [48,54], or even during sleep [55,56].…”

Section: Multi-dimensional Scalingmentioning

confidence: 99%

Neural Network based Successor Representations of Space and Language

Paul¹,

Schlieker²,

Schilling³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

How does the mind organize thoughts? The hippocampal-entorhinal complex is thought to support domain-general representation and processing of structural knowledge of arbitrary state, feature and concept spaces. In particular, it enables the formation of cognitive maps, and navigation on these maps, thereby broadly contributing to cognition. It has been proposed that the concept of multi-scale successor representations provides an explanation of the underlying computations performed by place and grid cells. Here, we present a neural network based approach to learn such representations, and its application to different scenarios: a spatial exploration task based on supervised learning, a spatial navigation task based on reinforcement learning, and a non-spatial task where linguistic constructions have to be inferred by observing sample sentences. In all scenarios, the neural network correctly learns and approximates the underlying structure by building successor representations. Furthermore, the resulting neural firing patterns are strikingly similar to experimentally observed place and grid cell firing patterns. We conclude that cognitive maps and neural network-based successor representations of structured knowledge provide a promising way to overcome some of the short comings of deep learning towards artificial general intelligence.

show abstract

Analysis and visualization of sleep stages based on deep neural networks

Cited by 35 publications

References 27 publications

Sleep as a random walk: a super-statistical analysis of EEG data across sleep stages

Sleep as a random walk: a super-statistical analysis of EEG data across sleep stages

Predictive coding and stochastic resonance as fundamental principles of auditory perception

Neural Network based Successor Representations of Space and Language

Contact Info

Product

Resources

About