5 Web page where I would keep sentences and phrases for week 1 from the articles I am reading terms
Related article for this week (1):
[Juhwan Noh et al. Inverse Design of Solid-State Materials via a Continuous Representation, Matter, vol. 1, no. 5, pp. 1370–1384, Nov. 2019. https://doi.org/10.1016/j.matt.2019.08.017 (accessed Feb. 10, 2022)].
H-index estimated using "web of science" database.
Authors:
[Noh, Juhwan - H-Index 10],
[Stein, Helge - H-Index 14]
Sanchez-Lengeling, Benjamin - H-Index 13
Autoencoder
noun
An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). The encoding is validated and refined by attempting to regenerate the input from the encoding. The autoencoder learns a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore insignificant data (“noise”). [https://en.wikipedia.org/wiki/Autoencoder]
Example: One example of a GM [Generative Model] is a variational autoencoder (VAE), composed of two deep neural networks, an encoder, and a decoder.
ru: Автоэнкодер, автокодировщик
Deep Learning
phrase
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised [https://en.wikipedia.org/wiki/Deep_learning].
Example: Recent advances in deep learning, availability of large high-quality datasets, and more affordable computation have propelled the inverse design of materials.
ru: глубокое обучение
Inverse Design
phrase
Contextual: In the considered article this phrase is related to the machine-learning models in materials science and means inverting the role of machine learning to generate a candidate material with selected properties. Machine learning models have been most extensively developed to predict the properties of candidate materials, which still requires the selection of candidates.
General: An inverse problem in science is the process of calculating from a set of observations the causal factors that produced them: for example, calculating an image in X-ray computed tomography, source reconstruction in acoustics, or calculating the density of the Earth from measurements of its gravity field. It is called an inverse problem because it starts with the effects and then calculates the causes. It is the inverse of a forward problem, which starts with the causes and then calculates the effects.
Example: The inverse design of new materials with desired properties is the ultimate goal of materials research
Contextual: The word “latent” means “hidden”. It is pretty much used that way in machine learning — you observe some data which is in the space that you can observe, and you want to map it to a latent space where similar data points are closer together [https://www.quora.com/What-is-the-meaning-of-latent-space].
Pretty clear explanation from considered scientific field: [https://towardsdatascience.com/understanding-latent-space-in-machine-learning-de5a7c687d8d]
Related phrase: A latent space, also known as a latent feature space or embedding space, is an embedding of a set of items within a manifold in which items which resemble each other more closely are positioned closer to one another in the latent space. Position within the latent space can be viewed as being defined by a set of latent variables that emerge from the resemblances from the objects.
In most cases, the dimensionality of the latent space is chosen to be lower than the dimensionality of the feature space from which the data points are drawn, making the construction of a latent space an example of dimensionality reduction, which can also be viewed as a form of data compression or machine learning.
A number of algorithms exist to create latent space embeddings given a set of data items and a similarity function.
[https://en.wikipedia.org/wiki/Latent_space]
General: In statistics, latent variables (from Latin: present participle of lateo (“lie hidden”), as opposed to observable variables) are variables that are not directly observed but are rather inferred (through a mathematical model) from other variables that are observed (directly measured). Mathematical models that aim to explain observed variables in terms of latent variables are called latent variable models. Latent variable models are used in many disciplines, including psychology, demography, economics, engineering, medicine, physics, machine learning/artificial intelligence, bioinformatics, chemometrics, natural language processing, econometrics, management and the social sciences. [https://en.wikipedia.org/wiki/Latent_variable]
ru: Прямого перевода в доступных источниках нет. Возможный перевод: скрытый вектор
Однако понятие несколько сложнее. Оно относится к очень новой области - генеративным состязательным сетям и мало употребляется в русско-язычных источниках. Ближайший русскоязычный термин относится к статистике - "скрытая переменная".
Solid-state
noun
the state of matter in which materials are not fluid but retain their boundaries without support, the atoms or molecules occupying fixed positions with respect to each other and unable to move freely
Example: Inverse Design of Solid-State Materials via a Continuous Representation
ru: Твердое состояние, более точный и специфичный перевод - конденсированное состояние
