With the growing volume of online information, recommender systems have been an effective strategy to overcome information overload. The utility of recommender systems cannot be overstated, given their widespread adoption in many web applications, along with their potential impact to ameliorate many problems related to over-choice. In recent years, deep learning has garnered considerable interest in many research fields such as computer vision and natural language processing, owing not only to stellar performance but also to the attractive property of learning feature representations from scratch. The influence of deep learning is also pervasive, recently demonstrating its effectiveness when applied to information retrieval and recommender systems research. The field of deep learning in recommender system is flourishing. This article aims to provide a comprehensive review of recent research efforts on deep learning-based recommender systems. More concretely, we provide and devise a taxonomy of deep learning-based recommendation models, along with a comprehensive summary of the state of the art. Finally, we expand on current trends and provide new perspectives pertaining to this new and exciting development of the field.

Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of task-specific training examples needed to adapt the model to a particular application. To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model (PaLM).We trained PaLM on 6144 TPU v4 chips using Pathways, a new ML system which enables highly efficient training across multiple TPU Pods. We demonstrate continued benefits of scaling by achieving state-ofthe-art few-shot learning results on hundreds of language understanding and generation benchmarks. On a number of these tasks, PaLM 540B achieves breakthrough performance, outperforming the finetuned stateof-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark. A significant number of BIG-bench tasks showed discontinuous improvements from model scale, meaning that performance steeply increased as we scaled to our largest model. PaLM also has strong capabilities in multilingual tasks and source code generation, which we demonstrate on a wide array of benchmarks. We additionally provide a comprehensive analysis on bias and toxicity, and study the extent of training data memorization with respect to model scale. Finally, we discuss the ethical considerations related to large language models and discuss potential mitigation strategies. * Equal Contribution. Author contributions and ordering details are listed in Appendix A.

Three-dimensional (3D) printing (also known as additive manufacturing) is an advanced manufacturing process that can produce complex shape geometries automatically from a three-dimensional computer-aided-design (CAD) model without any tooling, dies and fixtures. This automated manufacturing process has been applied to many diverse fields of industries today due to significant advantages of creating functional prototypes in reasonable build time with less human intervention and minimum material wastage. However, a more recent application of this technology towards the built environment seems to improve our traditional building strategies while reducing the need for human resources, high capital investments and additional formworks. Research interest in employing 3D printing for building and construction (B&C) has increased exponentially in the past few years. This paper reviews the latest research trends in the discipline by analysing publications from 1997 to 2016. Some recent developments for 3D concrete printing at the Singapore Centre for 3D Printing (SC3DP) are also discussed here. Finally, this paper gives a brief description of future work that can be done to improve both the capability and printing quality of the current systems.

Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example, Transformers have become an indispensable staple in the modern deep learning stack. Recently, a dizzying number of “X-former” models have been proposed - Reformer, Linformer, Performer, Longformer, to name a few - which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency . With the aim of helping the avid researcher navigate this flurry, this paper characterizes a large and thoughtful selection of recent efficiency-flavored “X-former” models, providing an organized and comprehensive overview of existing work and models across multiple domains.

The main advantage of 3D concrete printing (3DCP) is that it can manufacture complex, non-standard geometries and details rapidly using a printer integrated with a pump, hosepipe and nozzle. Sufficient speed is required for efficient and fast construction. The selected printing speed is a function of the size and geometrical complexity of the element to be printed, linked to the pump speed and quality of the extruded concrete material. Since the printing process requires a continuous, high degree of control of the material during printing, high performance building materials are preferred. Also, as no supporting formwork is used for 3DCP, traditional concrete cannot be directly used. From the above discussion, it is postulated that in 3DCP, the fresh properties of the material, printing direction and printing time may have significant effect on the overall load bearing capacity of the printed objects. The layered concrete may create weak joints in the specimens and reduce the load bearing capacity under compressive, tensile and flexural action that requires stress transfer across or along these joints.In this research, the 3D printed specimens are collected in different orientations from large 3DCP objects and tested for mechanical properties. For the materials tested, it is found that the mechanical properties such as compressive and flexural strength of 3D printed specimen are governed by its printing directions.