Refine
Has Fulltext
- no (4) (remove)
Year of publication
- 2020 (4) (remove)
Document Type
- Article (4)
Language
- English (4)
Is part of the Bibliography
- yes (4)
Keywords
- neural networks (4) (remove)
Institute
Supervised machine learning to assess methane emissions of a dairy building with natural ventilation
(2020)
A reliable quantification of greenhouse gas emissions is a basis for the development of adequate mitigation measures. Protocols for emission measurements and data analysis approaches to extrapolate to accurate annual emission values are a substantial prerequisite in this context. We systematically analyzed the benefit of supervised machine learning methods to project methane emissions from a naturally ventilated cattle building with a concrete solid floor and manure scraper located in Northern Germany. We took into account approximately 40 weeks of hourly emission measurements and compared model predictions using eight regression approaches, 27 different sampling scenarios and four measures of model accuracy. Data normalization was applied based on median and quartile range. A correlation analysis was performed to evaluate the influence of individual features. This indicated only a very weak linear relation between the methane emission and features that are typically used to predict methane emission values of naturally ventilated barns. It further highlighted the added value of including day-time and squared ambient temperature as features. The error of the predicted emission values was in general below 10%. The results from Gaussian processes, ordinary multilinear regression and neural networks were least robust. More robust results were obtained with multilinear regression with regularization, support vector machines and particularly the ensemble methods gradient boosting and random forest. The latter had the added value to be rather insensitive against the normalization procedure. In the case of multilinear regression, also the removal of not significantly linearly related variables (i.e., keeping only the day-time component) led to robust modeling results. We concluded that measurement protocols with 7 days and six measurement periods can be considered sufficient to model methane emissions from the dairy barn with solid floor with manure scraper, particularly when periods are distributed over the year with a preference for transition periods. Features should be normalized according to median and quartile range and must be carefully selected depending on the modeling approach.
Increased N400 amplitudes on indefinite articles (a/an) incompatible with expected nouns have been initially taken as strong evidence for probabilistic pre-activation of phonological word forms, and recently been intensely debated because they have been difficult to replicate. Here, these effects are simulated using a neural network model of sentence comprehension that we previously used to simulate a broad range of empirical N400 effects. The model produces the effects when the cue validity of the articles concerning upcoming noun meaning in the learning environment is high, but fails to produce the effects when the cue validity of the articles is low due to adjectives presented between articles and nouns during training. These simulations provide insight into one of the factors potentially contributing to the small size of the effects in empirical studies and generate predictions for cross-linguistic differences in article induced N400 effects based on articles’ cue validity. The model accounts for article induced N400 effects without assuming pre-activation of word forms, and instead simulates these effects as the stimulus-induced change in a probabilistic representation of meaning corresponding to an implicit semantic prediction error.
Increased N400 amplitudes on indefinite articles (a/an) incompatible with expected nouns have been initially taken as strong evidence for probabilistic pre-activation of phonological word forms, and recently been intensely debated because they have been difficult to replicate. Here, these effects are simulated using a neural network model of sentence comprehension that we previously used to simulate a broad range of empirical N400 effects. The model produces the effects when the cue validity of the articles concerning upcoming noun meaning in the learning environment is high, but fails to produce the effects when the cue validity of the articles is low due to adjectives presented between articles and nouns during training. These simulations provide insight into one of the factors potentially contributing to the small size of the effects in empirical studies and generate predictions for cross-linguistic differences in article induced N400 effects based on articles’ cue validity. The model accounts for article induced N400 effects without assuming pre-activation of word forms, and instead simulates these effects as the stimulus-induced change in a probabilistic representation of meaning corresponding to an implicit semantic prediction error.
We argue that natural language can be usefully described as quasi-compositional and we suggest that deep learning-based neural language models bear long-term promise to capture how language conveys meaning. We also note that a successful account of human language processing should explain both the outcome of the comprehension process and the continuous internal processes underlying this performance. These points motivate our discussion of a neural network model of sentence comprehension, the Sentence Gestalt model, which we have used to account for the N400 component of the event-related brain potential (ERP), which tracks meaning processing as it happens in real time. The model, which shares features with recent deep learning-based language models, simulates N400 amplitude as the automatic update of a probabilistic representation of the situation or event described by the sentence, corresponding to a temporal difference learning signal at the level of meaning. We suggest that this process happens relatively automatically, and that sometimes a more-controlled attention-dependent process is necessary for successful comprehension, which may be reflected in the subsequent P600 ERP component. We relate this account to current deep learning models as well as classic linguistic theory, and use it to illustrate a domain general perspective on some specific linguistic operations postulated based on compositional analyses of natural language. This article is part of the theme issue 'Towards mechanistic models of meaning composition'.