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
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
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
Being able to classify experienced emotions by identifying distinct neural responses has tremendous value in both fundamental research (e.g. positive psychology, emotion regulation theory) and in applied settings (clinical, healthcare, commercial). We aimed to decode the neural representation of the experience of two discrete emotions: sadness and disgust, devoid of differences in valence and arousal. In a passive viewing paradigm, we showed emotion evoking images from the International Affective Picture System to participants while recording their EEG. We then selected a subset of those images that were distinct in evoking either sadness or disgust (20 for each), yet were indistinguishable on normative valence and arousal. Event-related potential analysis of 69 participants showed differential responses in the N1 and EPN components and a support-vector machine classifier was able to accurately classify (58%) whole-brain EEG patterns of sadness and disgust experiences. These results support and expand on earlier findings that discrete emotions do have differential neural responses that are not caused by differences in valence or arousal.
DOCUMENT
Oscillatory neural dynamics have been steadily receiving more attention as a robust and temporally precise signature of network activity related to language processing. We have recently proposed that oscillatory dynamics in the beta and gamma frequency ranges measured during sentence-level comprehension might be best explained from a predictive coding perspective. Under our proposal we related beta oscillations to both the maintenance/change of the neural network configuration responsible for the construction and representation of sentence-level meaning, and to top-down predictions about upcoming linguistic input based on that sentence-level meaning. Here we zoom in on these particular aspects of our proposal, and discuss both old and new supporting evidence. Finally, we present some preliminary magnetoencephalography data from an experiment comparing Dutch subject- and object-relative clauses that was specifically designed to test our predictive coding framework. Initial results support the first of the two suggested roles for beta oscillations in sentence-level language comprehension.
DOCUMENT
Het doel van dit onderzoek is te onderzoeken onder welke omstandigheden en onder welke condities relatief moderne modelleringstechnieken zoals support vector machines, neural networks en random forests voordelen zouden kunnen hebben in medisch-wetenschappelijk onderzoek en in de medische praktijk in vergelijking met meer traditionele modelleringstechnieken, zoals lineaire regressie, logistische regressie en Cox regressie.
MULTIFILE
Analyzing historical decision-related data can help support actual operational decision-making processes. Decision mining can be employed for such analysis. This paper proposes the Decision Discovery Framework (DDF) designed to develop, adapt, or select a decision discovery algorithm by outlining specific guidelines for input data usage, classifier handling, and decision model representation. This framework incorporates the use of Decision Model and Notation (DMN) for enhanced comprehensibility and normalization to simplify decision tables. The framework’s efficacy was tested by adapting the C4.5 algorithm to the DM45 algorithm. The proposed adaptations include (1) the utilization of a decision log, (2) ensure an unpruned decision tree, (3) the generation DMN, and (4) normalize decision table. Future research can focus on supporting on practitioners in modeling decisions, ensuring their decision-making is compliant, and suggesting improvements to the modeled decisions. Another future research direction is to explore the ability to process unstructured data as input for the discovery of decisions.
MULTIFILE
This investigation explores relations between 1) a theory of human cognition, called Embodied Cognition, 2) the design of interactive systems and 3) the practice of ‘creative group meetings’ (of which the so-called ‘brainstorm’ is perhaps the best-known example). The investigation is one of Research-through-Design (Overbeeke et al., 2006). This means that, together with students and external stakeholders, I designed two interactive prototypes. Both systems contain a ‘mix’ of both physical and digital forms. Both are designed to be tools in creative meeting sessions, or brainstorms. The tools are meant to form a natural, element in the physical meeting space. The function of these devices is to support the formation of shared insight: that is, the tools should support the process by which participants together, during the activity, get a better grip on the design challenge that they are faced with. Over a series of iterations I reflected on the design process and outcome, and investigated how users interacted with the prototypes.
DOCUMENT
The huge number of images shared on the Web makes effective cataloguing methods for efficient storage and retrieval procedures specifically tailored on the end-user needs a very demanding and crucial issue. In this paper, we investigate the applicability of Automatic Image Annotation (AIA) for image tagging with a focus on the needs of database expansion for a news broadcasting company. First, we determine the feasibility of using AIA in such a context with the aim of minimizing an extensive retraining whenever a new tag needs to be incorporated in the tag set population. Then, an image annotation tool integrating a Convolutional Neural Network model (AlexNet) for feature extraction and a K-Nearest-Neighbours classifier for tag assignment to images is introduced and tested. The obtained performances are very promising addressing the proposed approach as valuable to tackle the problem of image tagging in the framework of a broadcasting company, whilst not yet optimal for integration in the business process.
DOCUMENT
