Refine
Document Type
- Preprint (4) (remove)
Language
- English (4)
Keywords
- Building with earth (1)
- Circular economy (1)
- Compressed earth (1)
- Decarbonization (1)
- Deep learning (1)
- Demolition wastes (1)
- Distributional regression (1)
- Low-carbon construction (1)
- Machine learning (1)
- Neural networks (1)
Contemporary empirical applications frequently require flexible regression models for complex response types and large tabular or non-tabular, including image or text, data. Classical regression models either break down under the computational load of processing such data or require additional manual feature extraction to make these problems tractable. Here, we present deeptrafo, a package for fitting flexible regression models for conditional distributions using a tensorflow backend with numerous additional processors, such as neural networks, penalties, and smoothing splines. Package deeptrafo implements deep conditional transformation models (DCTMs) for binary, ordinal, count, survival, continuous, and time series responses, potentially with uninformative censoring. Unlike other available methods, DCTMs do not assume a parametric family of distributions for the response. Further, the data analyst may trade off interpretability and flexibility by supplying custom neural network architectures and smoothers for each term in an intuitive formula interface. We demonstrate how to set up, fit, and work with DCTMs for several response types. We further showcase how to construct ensembles of these models, evaluate models using inbuilt cross-validation, and use other convenience functions for DCTMs in several applications. Lastly, we discuss DCTMs in light of other approaches to regression with non-tabular data.
An inter- and transdisciplinary concept has been developed, focusing on the scaling of industrial circular construction using innovative compacted mineral mixtures (CMM) derived from various soil types (sand, silt, clay) and recycled mineral waste. The concept aims to accelerate the systemic transformation of the construction industry towards carbon neutrality by promoting the large-scale adoption and automation of CMM-based construction materials, which incorporate natural mineral components and recycled aggregates or industrial by-products. In close collaboration with international and domestic stakeholders in the construction sector, the concept explores the integration of various CMM-based construction methods for producing wall elements in conventional building construction. Leveraging a digital urban mining platform, the concept aims to standardize the production process and enable mass-scale production. The ultimate goal is to fully harness the potential of automated CMM-based wall elements as a fast, competitive, emission-free, and recyclable alternative to traditional masonry and concrete construction techniques. To achieve this objective, the concept draws upon the latest advances in soil mechanics, rheology, and automation and incorporates open-source digital platform technologies to enhance data accessibility, processing, and knowledge acquisition. This will bolster confidence in CMM-based technologies and facilitate their widespread adoption. The extraordinary transfer potential of this approach necessitates both basic and applied research. As such, the proposed transformative, inter- and transdisciplinary concept will be conducted and synthesized using a comprehensive, holistic, and transfer-oriented methodology.
The main challenge in Bayesian models is to determine the posterior for the model parameters. Already, in models with only one or few parameters, the analytical posterior can only be determined in special settings. In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distributions. Usually, Gaussians are used as variational distributions (Gaussian-VI) which limits the quality of the approximation due to their limited flexibility. Transformation models on the other hand are flexible enough to fit any distribution. Here we present transformation model-based variational inference (TM-VI) and demonstrate that it allows to accurately approximate complex posteriors in models with one parameter and also works in a mean-field fashion for multi-parameter models like neural networks.
This paper introduces the concept of Universal Memory Automata (UMA) and automated compilation of Verilog Hardware Description Language (HDL) code at Register Transfer Level (RTL) from UMA graphs for digital designs. The idea is based on the observation that Push Down Automata (PDA) are able to process the Dyk-Language - commonly known as the balanced bracket problem - with a finite set of states while Finite State Machines (FSM) require an infinite set of states. Since infinite sets of states are not applicable to real designs, PDAs appear promising for types of problems similar to the Dyk-Language. PDAs suffer from the problem that complex memory operations need to be emulated by a specific stack management. The presented UMA therefore extends the PDA by other types of memory, e.g. Queue, RAM or CAM. Memories that are eligible for UMAs are supposed to have at least one read and one write port and a one-cycle read/write latency. With their modified state-transfer- and output-function, UMAs are able to operate user-defined numbers, configurations and types of memories. Proof of concept is given by an implementation of a cache coherency protocol, i.e. a practical problem in microprocessor design.