Unsupervised behaviour analysis and magnification (uBAM) using deep learning
نویسندگان
چکیده
Motor behaviour analysis is essential to biomedical research and clinical diagnostics as it provides a non-invasive strategy for identifying motor impairment its change caused by interventions. State-of-the-art instrumented movement time- cost-intensive, because requires the placement of physical or virtual markers. As well effort required marking keypoints annotations necessary training fine-tuning detector, users need know interesting beforehand provide meaningful keypoints. Here, we introduce unsupervised magnification (uBAM), an automatic deep learning algorithm analysing discovering magnifying deviations. A central aspect posture representations enable objective comparison movement. Besides quantifying deviations in behaviour, also propose generative model visually subtle differences directly video without requiring detour via annotations. Essential this deviations, even across different individuals, disentangling appearance behaviour. Evaluations on rodents human patients with neurological diseases demonstrate wide applicability our approach. Moreover, combining optogenetic stimulation shows suitability diagnostic tool correlating function brain plasticity. Being able precisely analyse study health disease, but often labour-intensive. Brattoli et al. develop approach based evaluate species diverse functions.
منابع مشابه
Text summarization using unsupervised deep learning
We present methods of extractive query-oriented single-document summarization using a deep auto-encoder (AE) to compute a feature space from the term-frequency (tf ) input. Our experiments explore both local and global vocabularies. We investigate the effect of adding small random noise to local tf as the input representation of AE, and propose an ensemble of such noisy AEs which we call the En...
متن کاملDeep Unsupervised Learning using Nonequilibrium Thermodynamics
A central problem in machine learning involves modeling complex data-sets using highly flexible families of probability distributions in which learning, sampling, inference, and evaluation are still analytically or computationally tractable. Here, we develop an approach that simultaneously achieves both flexibility and tractability. The essential idea, inspired by non-equilibrium statistical ph...
متن کاملPredicting Process Behaviour using Deep Learning
Predicting business process behaviour is an important aspect of business process management. Motivated by research in natural language processing, this paper describes an application of deep learning with recurrent neural networks to the problem of predicting the next event in a business process. This is both a novel method in process prediction, which has largely relied on explicit process mod...
متن کاملCliqueCNN: Deep Unsupervised Exemplar Learning
Exemplar learning is a powerful paradigm for discovering visual similarities in an unsupervised manner. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of Convolutional Neural networ...
متن کاملAutoencoders, Unsupervised Learning, and Deep Architectures
Autoencoders play a fundamental role in unsupervised learning and in deep architectures for transfer learning and other tasks. In spite of their fundamental role, only linear autoencoders over the real numbers have been solved analytically. Here we present a general mathematical framework for the study of both linear and non-linear autoencoders. The framework allows one to derive an analytical ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Nature Machine Intelligence
سال: 2021
ISSN: ['2522-5839']
DOI: https://doi.org/10.1038/s42256-021-00326-x