From the article: Abstract: An overview of neural network architectures is presented. Some of these architectures have been created in recent years, whereas others originate from many decades ago. Apart from providing a practical tool for comparing deep learning models, the Neural Network Zoo also uncovers a taxonomy of network architectures, their chronology, and traces back lineages and inspirations for these neural information processing systems.
DOCUMENT
We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
The recent success of Machine Learning encouraged research using artificial neural networks (NNs) in computer graphics. A good example is the bidirectional texture function (BTF), a data-driven representation of surface materials that can encapsulate complex behaviors that would otherwise be too expensive to calculate for real-time applications, such as self-shadowing and interreflections. We propose two changes to the state-of-the-art using neural networks for BTFs, specifically NeuMIP. These changes, suggested by recent work in neural scene representation and rendering, aim to improve baseline quality, memory footprint, and performance. We conduct an ablation study to evaluate the impact of each change. We test both synthetic and real data, and provide a working implementation within the Mitsuba 2 rendering framework. Our results show that our method outperforms the baseline in all these metrics and that neural BTF is part of the broader field of neural scene representation. Project website: https://traverse-research.github.io/NeuBTF/.
DOCUMENT
A considerable amount of literature has been published on Corporate Reputation, Branding and Brand Image. These studies are extensive and focus particularly on questionnaires and statistical analysis. Although extensive research has been carried out, no single study was found which attempted to predict corporate reputation performance based on data collected from media sources. To perform this task, a biLSTM Neural Network extended with attention mechanism was utilized. The advantages of this architecture are that it obtains excellent performance for NLP tasks. The state-of-the-art designed model achieves highly competitive results, F1 scores around 72%, accuracy of 92% and loss around 20%.
DOCUMENT
This paper presents a case study where a model predictive control (MPC) logic is developed for energy flexible operation of a space heating system in an educational building. A Long Short-Term Memory Neural Network (LSTM) surrogate model is trained on the output of an EnergyPlus building simulation model. This LSTM model is used within an MPC framework where a genetic algorithm is used to optimize setpoint sequences. The EnergyPlus model is used to validate the performance of the control logic. The MPC approach leads to a substantial reduction in energy consumption (7%) and energy costs (13%) with improved comfort performance. Additional energy costs savings are possible (7–16%) if a sacrifice in indoor thermal comfort is accepted. The presented method is useful for developing MPC systems in the design stages where measured data is typically not available. Additionally, this study illustrates that LSTM models are promising for MPC for buildings.
DOCUMENT
Channel State Information (CSI) analysis for Predictive Maintenance using Convolutiona Neural Network (CNN).
MULTIFILE
There is a growing literature investigating the relationship between oscillatory neural dynamics measured using electroencephalography (EEG) and/or magnetoencephalography (MEG), and sentence-level language comprehension. Recent proposals have suggested a strong link between predictive coding accounts of the hierarchical flow of information in the brain, and oscillatory neural dynamics in the beta and gamma frequency ranges. We propose that findings relating beta and gamma oscillations to sentence-level language comprehension might be unified under such a predictive coding account. Our suggestion is that oscillatory activity in the beta frequency range may reflect both the active maintenance of the current network configuration responsible for representing the sentence-level meaning under construction, and the top-down propagation of predictions to hierarchically lower processing levels based on that representation. In addition, we suggest that oscillatory activity in the low and middle gamma range reflect the matching of top-down predictions with bottom-up linguistic input, while evoked high gamma might reflect the propagation of bottom-up prediction errors to higher levels of the processing hierarchy. We also discuss some of the implications of this predictive coding framework, and we outline ideas for how these might be tested experimentally.
LINK
Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and meteorological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be Gated Recurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
DOCUMENT
Objective. In this study it was investigated whether an artificial neural network can be used to determine the horizontal, fore-aft component of the ground reaction force from insole pressure patterns. Design. An artificial neural network was applied to map insole pressures and ground reaction forces. Method. To train an artificial neural network insole pressure patterns and ground reaction force data were simultaneously determined for a wide range of different speeds (0.9-2.3 m s−1) for five subjects. Both intrasubject and intersubject generalizability were evaluated. Results. At the intrasubject level generalizability was good when the speed for which the force was to be predicted was within the range of speeds from which data were used to train the network. Besides in some cases, generalizability to a condition outside the range of training conditions could be demonstrated. At the intersubject level the quality of generalization differed widely over subjects, from poor to good. Conclusions. It was found that an artificial neural network is able to map the relationship between insole pressure patterns and the fore-aft component of the ground reaction force. Relevance Good intrasubject generalization of 'knowledge' obtained by an artificial neural network will allow the assessment of the fore-aft component of ground reaction force in condition that cannot be evaluated with force plates, e.g. activities of daily living or real sport situations. Additionally, intersubject generalization will allow shear-force recordings in subjects that are not able to complete a great number of runs to acquire enough force-plate hits.
DOCUMENT
Passenger flow management is an important issue at many airports around the world. There are high concentrations of passengers arriving and leaving the airport in waves of large volumes in short periods, particularly in big hubs. This might cause congestion in some locations depending on the layout of the terminal building. With a combination of real airport data, as well as synthetic data obtained through an airport simulator, a Long Short-Term Memory Recurrent Neural Network has been implemented to predict the possible trajectories that passengers may travel within the airport depending on user-defined passenger profiles. The aim of this research is to improve passenger flow predictability and situational awareness to make a more efficient use of the airport, that could also positively impact communication with public and private land transport operators.
DOCUMENT
