Concepts and applications of Deep Learning이라는 제목으로 Concepts and Applications of Deep Learning (ukessays.com) 에 올라온 에세이

한동훈 딸이 IEEE Machine Learning in Healthcare - Application of Advanced Computational Techniques to Improve Healthcare | IEEE Conference Publication | IEEE Xplore 에 올린 "논문"

Abstract 내용

[Since 2006, Deep Learning, also known as Hierarchal Leaning has been evolved as a new field of Machine Learning Research. The deep learning model deals with problems on which shallow architectures (e.g. Regression) are affected by the curse of dimensionality. As part of a two-stage learning scheme involving multiple layers of nonlinear processing a set of statistically robust features is automatically extracted from the data. The present tutorial introducing the deep learning special session details the state-of-the-art models and summarizes the current understanding of this learning approach which is a reference for many difficult classification tasks. Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text.]

이건 Concepts and applications of Deep Learning

[Since 2006, Deep Learning, also known as Hierarchical Learning, has developed as a new field of research in Machine Learning. Deep learning models are used to solve problems that shallow architectures (e.g., regression) cannot solve due to the curse of dimensionality. Automatically created statistically robust characteristics are derived from the data using a two-stage learning procedure that incorporates multiple layers of nonlinear processing. This review article, which serves as the introduction to the special session on deep learning, provides state-of-the-art models and summarizes current understanding on this type of learning method, which is used to tackle a variety of difficult categorization tasks. Deep Learning is a relatively recent area of research in Machine Learning that was founded with the purpose of getting Machine Learning closer to one of its original objectives: Artificial Intelligence. Deep Learning is concerned with the acquisition of several levels of representation and abstraction that aid in the interpretation of various forms of data, including images, audio, and text.]

이건 한동훈 딸 논문. 읽어보면 알겠지만 의도적으로 단어와 문장구조를 몇번 바꾸긴 했지만, 대놓고 배꼈음

Introduction 내용

[Just consider we have to identify someone’s handwriting. The people have different ways of writing, for example, the numbers-Whether they write a ‘7’ or a ‘9’. We know that if there is a close loop on the top of the vertical line then we named it as ‘9’ and if it contains a horizontal line instead of loop then we think it is ‘7’. The thing we used for exact recognition of digit is a smart display of setting smaller features together to make the whole – detecting distinguished edges to make lines, observing a horizontal vs. vertical line, seeing the positioning of the vertical section under the horizontal section, detecting a loop in the horizontal section, etc.

The idea of the deep learning is the same: find out multiple levels of features that work jointly to define increasingly more abstract aspects of the data.

So, Deep Learning is defined as follows:

“A sub-field of machine learning that is based on learning several levels of representations, corresponding to a hierarchy of features or factors or concepts, where higher-level concepts are defined from lower-level ones, and the same lower-level concepts can help to define many higher-level concepts. Deep learning is part of a broader family of machine learning methods based on learning representations. An observation (e.g., an image) can be represented in many ways (e.g., a vector of pixels), but some representations make it easier to learn tasks of interest (e.g., is this the image of a human face?) from examples, and research in this area attempts to define what makes better representations and how to learn them.” see Wikipedia on “Deep Learning” as of this writing in February 2013; see http://en.wikipedia.org/wiki/Deep_learning.]

여기까지 Concepts and applications of Deep Learning 내용

[Consider the situation in which we must recognize someone's handwriting. Individuals have distinct writing styles, for example, when it comes to numbers whether they write a '7' or a '9'. We know that if the vertical line has a near loop at the top, it is a '9'; if the vertical line contains a horizontal line instead of a loop, it is a '7'. The method employed was for precise digit identification is a smart display that combines tiny features identifying distinct edges to form lines, observing a horizontal vs. vertical line, seeing the vertical part underneath the horizontal section, detecting a loop in the horizontal section, and so on. Deep learning is based on the same principle: identify many layers of characteristics that operate in concert to describe progressively abstract parts of the data.

As a result, the term "Deep Learning" is defined as follows:

"A subfield of machine learning that is based on learning multiple levels of representations, each of which corresponds to a hierarchy of features, factors, or concepts, with higher-level concepts defined by lower-level concepts and the same lower-level concepts assisting in the definition of numerous higherlevel concepts (Glorot et al., 2011a). Known as deep learning, this technique is part of a larger family of machine learning algorithms that are founded on the principle of representation learning. The representation of an observation (for example, a picture of a face) can be represented in a variety of ways (for example, as a vector of pixels), and research in this area seeks to define what constitutes superior representations and how to learn them from examples.]

한동훈 딸 논문 내용. 대놓고 부사구와 접속사 위주로만 바꿨고, 구조 똑같음