Unsupervised Object-Centric Learning From Multiple Unspecified Viewpoints.

Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a multi-object visual scene from multiple viewpoints, humans can perceive the scene compositionally from each viewpoint while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold. This ability is essential for humans to identify the same object while moving and to learn from vision efficiently. It is intriguing to design models that have a similar ability. In this article, we consider a novel problem of learning compositional scene representations from multiple unspecified (i.e., unknown and unrelated) viewpoints without using any supervision and propose a deep generative model which separates latent representations into a viewpoint-independent part and a viewpoint-dependent part to solve this problem. During the inference, latent representations are randomly initialized and iteratively updated by integrating the information in different viewpoints with neural networks. Experiments on several specifically designed synthetic datasets have shown that the proposed method can effectively learn from multiple unspecified viewpoints.

Compositional Scene Representation Learning via Reconstruction: A Survey.

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable for artificial intelligence to have similar abilities. Compositional scene representation learning is a task that enables such abilities. In recent years, various methods have been proposed to apply deep neural networks, which have been proven to be advantageous in representation learning, to learn compositional scene representations via reconstruction, advancing this research direction into the deep learning era. Learning via reconstruction is advantageous because it may utilize massive unlabeled data and avoid costly and laborious data annotation. In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.

Computing mathematical functions with chemical reactions via stochastic logic.

This paper presents a novel strategy for computing mathematical functions with molecular reactions, based on theory from the realm of digital design. It demonstrates how to design chemical reaction networks based on truth tables that specify analog functions, computed by stochastic logic. The theory of stochastic logic entails the use of random streams of zeros and ones to represent probabilistic values. A link is made between the representation of random variables with stochastic logic on the one hand, and the representation of variables in molecular systems as the concentration of molecular species, on the other. Research in stochastic logic has demonstrated that many mathematical functions of interest can be computed with simple circuits built with logic gates. This paper presents a general and efficient methodology for translating mathematical functions computed by stochastic logic circuits into chemical reaction networks. Simulations show that the computation performed by the reaction networks is accurate and robust to variations in the reaction rates, within a log-order constraint. Reaction networks are given that compute functions for applications such as image and signal processing, as well as machine learning: arctan, exponential, Bessel, and sinc. An implementation is proposed with a specific experimental chassis: DNA strand displacement with units called DNA "concatemers".

Improved stabilization of coix seed oil in a nanocage-coating framework based on gliadin-carboxymethyl chitosan-Ca2.

Coix seed oil (CSO) is easily suffered functional-loss by oxidation and hydrothermal-treatment. The environmental stable nanocage-coating-CSO particles (OGC-Ca) by the frameworks consist of gliadins, carboxymethyl chitosan (CMCS) and Ca2+ were investigated. Results showed Ca2+ was the key controller for fabricating this nanocage-coating-frameworks, bridging macromolecule-chains with electrostatic interaction and hydrogen bonds, detected by FTIR, CD, DSC and XRD. SEM displayed new-formed velvet-like twigs after cross-linking CMCS to gliadins. Ca2+ assisted the nanocage-coating by significant down-sizing conversion OGC to OGC-Ca with consumption of twigs. OGC-Ca displayed a good stability towards heat (60-80 °C, 0-80 min), pH (3-8), NaCl (0-0.5 mM), storage (4/25 °C, 12 days), and a reduce of the pre-oxidation value of CSO in water and the improved controlled release of CSO in simulated GI tract. It illustrated GC-Ca frameworks would be a suitable delivery carrier for the CSO like pharmaceuticals and nutraceuticals for the food or medical use.