This essay are used to collect excellent sentences or vocabularies in paper writing releated to machine learning.

Sentences

Describe our method

• In this section, we evaluate the superior aspects as well as the limitations of the proposed model by taking into account the state-of-art models
• The results show that EVGO outperforms all the algorithms in comparison for all experiments.

• Our work, which takes the hybrid approach of developing a population-based model that is then adjusted to COVID-19 mortality rates, has several strengths.
• This work also has several limitations. first,second,third
• The correction method used in this study, using a linear probability model, is coarse, and could result in significant bias if the populations are sufficiently different.
• Last and most important, without individual-level data, there is no way to test the resulting predictions.
• The process consists of two steps: first the formation of chromate/phosphate treated layer on the surface of aluminium and secondly anodizing in a sulphuric acid solution.
• The proposed LoTeNet model is used to learn decision functions in high dimensional spaces in a supervised learning set-up and is optimized end-toend by backpropagating the error signal through the tensor network.

Introduce others’ work

• Examples of research in this ares include [1-3]. Much of this work concerns…
• The scientific workflow for the majority of empirical studies, starting with a predefined research question and proceeding with
• Part of the research challenges faced in this field has thus been transferred to the computer scirence domain.。
• A variety of measures have been suggested for describing the accuracy of land-cover classifications.
• Numerous accuracy measures have been proposed for summarizing the information contained in this error matrix

Phrase

• Last and most important/Last but not least
• From then on、But in addition to this、Essentially、 Subsequent developments generalized this to other scenarios、Moreover、In particular、in principle、As such、Generally speaking、For instance、 In the modern formulation、fall short. 、see the light 、it was the promise of harnessing

Vocabulary

In some practical scenieso, especially in medicine and health care,

Merits

Tensor

《Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition》Longhao Yuan

• Tensors are high-dimension representations of vectors and matrices. Many kinds of data in real-world, for example, color images (length × width × RGB channels), videos (length × width × RGB channels × time) and electroencephalography (EEG) signals (magnitude×trails×time) are more than two dimensions

• Tensor representation can retain the high dimension of data and solve the above problems. Tensor has been studied for more than a century, many methodologies have been proposed [14]. Moreover, tensor has been applied in various research field such as signal processing [6], machine learning [2], data completion [1], brain-computer interface (BCI) [16], etc…

Tensor network

Field Tensor Network State [1]

• Tensor networks (TN) are becoming a key tool to describe many-body quantum systems [1]. On the one hand, they can efficiently approximate quantum states of local Hamiltonians in thermal equilibrium, which has led to powerful numerical algorithms with applications in condensed matter and, to some extent, in high-energy physics [2]. On the other hand, they provide us with paradigmatic examples of strongly correlated states and thus allow us to investigate intriguing many-body quantum phenomena. For instance, they offer us a guide to classify symmetry protected topological phases [3, 4], or to understand a large variety of topologically ordered behavior.

Tensor networks for complex quantum system [2]

• From then on, developments on TN methods continued mostly at the crossover of condensed matter physics and quantum information. But in addition to this, it came as a pleasant surprise that TNs were also relevant in other scientific areas. Examples are quantum gravity, where the MERA has been proposed to be linked to geometry of space, e.g… via the Anti-de Sitter / Conformal Field Theory correspondence (AdS/CFT) [14], and artificial intelligence, where it has been proven that neural networks have a TN structure [15]. And more applications are being found every day, sometimes in the most unexpected places. Essentially, anywhere that there is a structure of correlations, there is also a TN, meaning that there is room to apply our knowledge on quantum many-body entanglement.

Tensor network decompositions in the presence of a global symmetry [3]

• Importantly, in a lattice made of N sites, where the Hilbert space dimension grows exponentially with N, TN decompositions often offer an efficient description

Machine Learning with Tensor Networks（Book）[4]

• Inspired by the success of tensor network decompositions to capture the relevant correlations in quantum many-body physics, machine learning models based on tensor network decompositions to describe the correlation structure in data will be studied. Only very recently it has been put forward that TN’s could be viable candidate in the field of big data science and statistical learning and in the next section a short overview will be given of the work that is already done on this topic.

Referrences

1. Nielsen, A. E. B., Herwerth, B., Cirac, J. I., & Sierra, G. (2020). Field Tensor Network States. ArXiv.
2. Orús, R. (2019). Tensor networks for complex quantum systems. Nature Reviews Physics, 1(9), 538–550. https://doi.org/10.1038/s42254-019-0086-7
3. Singh, S., Pfeifer, R. N. C., & Vidal, G. (2010). Tensor network decompositions in the presence of a global symmetry. Physical Review A - Atomic, Molecular, and Optical Physics, 82(5), 1–4. https://doi.org/10.1103/PhysRevA.82.050301
4. Stoudenmire, & Edwin. (2020). Machine Learning with Tensor Networks. Bulletin of the American Physical Society.