Results 31 to 40 of about 443,352 (208)
Physically Embodied Deep Image Optimisation [PDF]
5th Workshop on Machine Learning for Creativity and Design of the
Neural Information Processing Systems (NeurIPS) 2021 Conference, 2022 Physical sketches are created by learning programs to control a drawing robot. A differentiable rasteriser is used to optimise sets of drawing strokes to match an input image, using deep networks to provide an encoding for which we can compute a loss. The optimised drawing primitives can then be translated into G-code commands which command a robot to ...
arxiv
Circular and square cups drawing and ironing of Ti alloy sheets by incremental press forming method [PDF]
MATEC Web of ConferencesThe low ductility of Ti–6Al–4V alloy at forming temperatures below 780°C is still a problem. Ti–6Al–IV alloy is usually hot press formed at 780 to 900°C.
Okude Yusuke +4 more
doaj +1 more source
Depth-dependent warming of the Gulf of Eilat (Aqaba) [PDF]
arXiv, 2023 The Gulf of Eilat (Gulf of Aqaba) is a semi-enclosed basin situated at the northern end of the Red Sea, renowned for its exceptional marine ecosystem. To evaluate the response of the Gulf to climate variations, we analyzed various factors including temperature down to 700 m, surface air temperature, and heat fluxes.
arxiv
Frontiers in Materials, 2019 The influence of rolling and annealing on the resulting mechanical properties and forming behavior of Mg-Zn-RE and Mg-Zn-Ca alloys produced via twin roll casting is investigated. After hot rolling followed by an annealing treatment, both alloys develop a
José Victoria-Hernández +3 more
doaj +1 more source
Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning [PDF]
arXiv, 2021 AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play. Many researchers are looking for ways to reproduce and improve results for other games/tasks.
arxiv
Journal of Manufacturing Processes, 2020 Abstract Warm Hydromechanical Deep Drawing (WHDD) is considered as an effective sheet metal forming process to overcome low formability problems of lightweight materials, such as aluminum and magnesium alloys, at room temperature. WHDD process combines the advantages of Hydromechanical Deep Drawing (HDD) and Warm Deep Drawing (WDD) processes. In this
Muammer Koç +6 more
openaire +3 more sources
Deep Vectorization of Technical Drawings [PDF]
, 2020 We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-based network to estimate vector primitives, and (3 ...
arxiv +1 more source
Experimental and numerical studies on the warm deep drawing of an Al–Mg alloy
International Journal of Mechanical Sciences, 2015 Abstract The warm deep drawing of circular AA5754-O aluminium alloy blanks was investigated both experimentally using specially designed equipment and numerically using a fully coupled thermo-mechanical finite element model. Cylindrical cups were prepared with a heated die and blank-holder.
H. Laurent +4 more
openaire +3 more sources
A massive warm baryonic halo in the Coma cluster [PDF]
Astrophys.J. 585 (2003) 722-729, 2002 Several deep PSPC observations of the Coma cluster reveal a very large-scale halo of soft X-ray emission, substantially in excess of the well known radiation from the hot intra-cluster medium. The excess emission, previously reported in the central region of the cluster using lower-sensitivity EUVE and ROSAT data, is now evident out to a radius of 2.6 ...
arxiv +1 more source
Deep Neural Network for DrawiNg Networks, (DNN)^2 [PDF]
arXiv, 2021 By leveraging recent progress of stochastic gradient descent methods, several works have shown that graphs could be efficiently laid out through the optimization of a tailored objective function. In the meantime, Deep Learning (DL) techniques achieved great performances in many applications.
arxiv