Neural style transfer is a well-known branch of deep learning research, with many interesting works and two major drawbacks. Most of the works in the field are hard to use by non-expert users and substantial hardware resources are required. In this work, we present a solution to both of these problems. We have applied neural style transfer to real-time video (over 25 frames per second), which is capable of running on mobile devices. We also investigate the works on achieving temporal coherence and present the idea of fine-tuning, already trained models, to achieve stable video. What is more, we also analyze the impact of the common deep neural network architecture on the performance of mobile devices with regard to number of layers and filters present. In the experiment section we present the results of our work with respect to the iOS devices and discuss the problems present in current Android devices as well as future possibilities. At the end we present the qualitative results of stylization and quantitative results of performance tested on the iPhone 11 Pro and iPhone 6s. The presented work is incorporated in Kunster - AR Art Video Maker application available in the Apple's App Store.

In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigate multi-encoder approaches in documentlevel neural machine translation (NMT). Surprisingly, we find that the context encoder does not only encode the surrounding sentences but also behaves as a noise generator. This makes us rethink the real benefits of multi-encoder in context-aware translation - some of the improvements come from robust training. We compare several methods that introduce noise and/or well-tuned dropout setup into the training of these encoders. Experimental results show that noisy training plays an important role in multi-encoder-based NMT, especially when the training data is small. Also, we establish a new state-of-the-art on IWSLT Fr-En task by careful use of noise generation and dropout methods.

Neural machine translation (NMT) needs large parallel corpora for state-of-the-art translation quality. Low-resource NMT is typically addressed by transfer learning which leverages large monolingual or parallel corpora for pre-training. Monolingual pre-training approaches such as MASS (MAsked Sequence to Sequence) are extremely effective in boosting NMT quality for languages with small parallel corpora. However, they do not account for linguistic information obtained using syntactic analyzers which is known to be invaluable for several Natural Language Processing (NLP) tasks. To this end, we propose JASS, Japanese-specific Sequence to Sequence, as a novel pre-training alternative to MASS for NMT involving Japanese as the source or target language. JASS is joint BMASS (Bunsetsu MASS) and BRSS (Bunsetsu Reordering Sequence to Sequence) pre-training which focuses on Japanese linguistic units called bunsetsus. In our experiments on ASPEC Japanese--English and News Commentary Japanese--Russian translation we show that JASS can give results that are competitive with if not better than those given by MASS. Furthermore, we show for the first time that joint MASS and JASS pre-training gives results that significantly surpass the individual methods indicating their complementary nature. We will release our code, pre-trained models and bunsetsu annotated data as resources for researchers to use in their own NLP tasks.

Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks.

However, existing works based on this observation require training and evaluating a large number of structures, which limits their application.

In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure.

Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint).

In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process.

In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2.

Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings. The code is available at https://github.com/zx55/dmcp

Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed KERN model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.

Spiking neural networks (SNNs) are considered as a potential candidate to overcome current challenges such as the high-power consumption encountered by artificial neural networks (ANNs), however there is still a gap between them with respect to the recognition accuracy on practical tasks. A conversion strategy was thus introduced recently to bridge this gap by mapping a trained ANN to an SNN. However, it is still unclear that to what extent this obtained SNN can benefit both the accuracy advantage from ANN and high efficiency from the spike-based paradigm of computation. In this paper, we propose two new conversion methods, namely TerMapping and AugMapping. The TerMapping is a straightforward extension of a typical threshold-balancing method with a double-threshold scheme, while the AugMapping additionally incorporates a new scheme of augmented spike that employs a spike coefficient to carry the number of typical all-or-nothing spikes occurring at a time step. We examine the performance of our methods based on MNIST, Fashion-MNIST and CIFAR10 datasets. The results show that the proposed double-threshold scheme can effectively improve accuracies of the converted SNNs. More importantly, the proposed AugMapping is more advantageous for constructing accurate, fast and efficient deep SNNs as compared to other state-of-the-art approaches. Our study therefore provides new approaches for further integration of advanced techniques in ANNs to improve the performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic computing.

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1\%/4.6\% without external language model (LM), 1.9\%/4.1\% with LM and 2.9\%/7.0\% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0\%/4.6\% with LM and 3.9\%/11.3\% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.

Neural networks have opened up many new opportunities to utilize remotely sensed images in meteorology. Common applications include image classification, e.g., to determine whether an image contains a tropical cyclone, and image translation, e.g., to emulate radar imagery for satellites that only have passive channels. However, there are yet many open questions regarding the use of neural networks in meteorology, such as best practices for evaluation, tuning and interpretation. This article highlights several strategies and practical considerations for neural network development that have not yet received much attention in the meteorological community, such as the concept of effective receptive fields, underutilized meteorological performance measures, and methods for NN interpretation, such as synthetic experiments and layer-wise relevance propagation. We also consider the process of neural network interpretation as a whole, recognizing it as an iterative scientist-driven discovery process, and breaking it down into individual steps that researchers can take. Finally, while most work on neural network interpretation in meteorology has so far focused on networks for image classification tasks, we expand the focus to also include networks for image translation.

Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation and features pseudo visual pivoting in which we learn a shared multilingual visual-semantic embedding space and incorporate visually-pivoted captioning as additional weak supervision. The experimental results on the widely used Multi30K dataset show that the proposed model significantly improves over the state-of-the-art methods and generalizes well when the images are not available at the testing time.

Dialogue engines that incorporate different types of agents to converse with humans are popular.

However, conversations are dynamic in the sense that a selected response will change the conversation on-the-fly, influencing the subsequent utterances in the conversation, which makes the response selection a challenging problem.

We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents by taking into account the conversational history, and propose a emph{Neural Response Selection} method.

The proposed method is trained to predict a coherent set of responses within a single conversation, considering its own predictions via a curriculum training mechanism.

Our experimental results show that the proposed method can accurately select the most appropriate responses, thereby significantly improving the user experience in dialogue systems.

Making changes to a program to optimize its performance is an unscalable task that relies entirely upon human intuition and experience. In addition, companies operating at large scale are at a stage where no single individual understands the code controlling its systems, and for this reason, making changes to improve performance can become intractably difficult. In this paper, a learning system is introduced that provides AI assistance for finding recommended changes to a program. Specifically, it is shown how the evaluative feedback, delayed-reward performance programming domain can be effectively formulated via the Monte Carlo tree search (MCTS) framework. It is then shown that established methods from computational games for using learning to expedite tree-search computation can be adapted to speed up computing recommended program alterations. Estimates of expected utility from MCTS trees built for previous problems are used to learn a sampling policy that remains effective across new problems, thus demonstrating transferability of optimization knowledge. This formulation is applied to the Apache Spark distributed computing environment, and a preliminary result is observed that the time required to build a search tree for finding recommendations is reduced by up to a factor of 10x.

A new study suggests that vulnerability to CTE is not limited to professional athletes.

See the Code - See it Full Page - See Details

This Pen uses: Pug, SCSS, JavaScript, and

After Governor Jay Inslee announced a prohibition on gatherings of 250 people or more in three Washington counties (Snohomish, King, Pierce) on Wednesday, and with public health concerns growing over the COVID-19 pandemic, many organizations in Spokane are following suit. The Inlander will be frequently updating its online calendar of events to reflect local cancelations as we hear of them.…

Ask any working musician why they play live, why they lug their equipment to and from bars and restaurants and wine-tasting rooms week after week, and they'll point to the same nebulous thing: It's the connection with an audience.…

THE SHOW WILL GO ON…

While events around the country have been put on hold, Coeur d’Alene’s Summer Theatre is still slated for a show at the end of the month. But it won’t be in the usual format.…

Two beloved Spokane-based entertainers are teaming up this weekend for a good cause.…

The Inlander is a community newspaper covering news, politics, events, happy hour, everything that's happening today, things to do on the weekend, in Spokane, Coeur d'Alene, the greater Inland Northwest and beyond.

[IMAGE-1] Midtown Coeur d'Alene. The pedestrian-friendly strip of restaurants and shops that runs north-south along Fourth Street in between Garden and Harrison avenues.…

The invention relates to protein binding interacting/binding compounds and methods of identifying and using them. The invention further relates to pharmaceutical compositions and methods for treating 5-HT2C and/or RSK disorders, including diseases and disorders mediated by GPCRs and/or RSKs.

A spiking neuron-based working memory device is provided. The spiking neuron-based working memory device includes an input interface configured to convert input spike signals into respective burst signals having predetermined forms, and output a sequence of the burst signals, the burst signals corresponding to the input spike signals in a burst structure, and two or more memory elements (MEs) configured to sequentially store features respectively corresponding to the outputted sequence of the burst signals, each of the MEs continuously outputting spike signals respectively corresponding to the stored features.

Dental compositions are provided comprising a compound of Formula (I) or a pharmaceutically acceptable salt thereof: wherein n is an integer from about 2 to about 5.

An object of the present invention is to provide a novel trans-2-decenoic acid derivative or a pharmaceutically acceptable salt thereof and to provide a pharmaceutical agent which contains said compound as an active ingredient and has a highly safe neurotrophic factor-like activity or an alleviating action for side effect induced by administration of anti-cancer agents. The trans-2-decenoic acid derivative or a pharmaceutically acceptable salt thereof which is the compound of the present invention is specifically represented by the formula (1): (In the formula, Y is —O—, —NR— or —S—, R is hydrogen atom, alkyl group, dialkylaminoalkyl group or the like and W is a substituent such as dialkylaminoalkyl group) and has a quite high usefulness as a pharmaceutical agent such as a preventive or therapeutic agent for dementia, Alzheimer's disease, Parkinson's disease, depression, etc., a treating or repairing agent for spinal cord injury.

Bioassays for detecting the ability of one sample of a food substance, nutritional supplement, therapeutic agent and/or disease preventive agent relative to that of a second sample of such a substance, supplement and/or agent to inhibit, upregulate or otherwise modulate translation initiation, and thereby demonstrate a disease curative and/or preventive effect in a human and/or animal that consumes a such substance, supplement and/or agent or to whom a such substance, supplement and/or agent is administered are provided.

The invention relates to ceramide dimers which are constructed from two ceramide molecules which are crosslinked to each other via their lipophilic end. The ceramide molecules thereby have at least one hydrophilic group at their hydrophilic end for increasing the hydration shell of the dimer. The ceramide dimers according to the invention can be used as pharmaceutical preparation or as cosmetic preparation.

The present invention pertains generally to the field of therapeutic compounds. More specifically the present invention pertains to certain pyridyl-amino-pyrazine carbonitrile compounds that, inter alia, inhibit Checkpoint Kinase 1 (CHK1) kinase function. The present invention also pertains to pharmaceutical compositions comprising such compounds, and the use of such compounds and compositions, both in vitro and in vivo, to inhibit CHK1 kinase function, and in the treatment of diseases and conditions that are mediated by CHK1, that are ameliorated by the inhibition of CHK1 kinase function, etc., including proliferative conditions such as cancer, etc., optionally in combination with another agent, for example, (a) a DNA topoisomerase I or II inhibitor; (b) a DNA damaging agent; (c) an antimetabolite or thymidylate synthase (TS) inhibitor; (d) a microtubule targeted agent; and (e) ionizing radiation.

The present invention relates to a novel acid addition salt of risperidone, wherein acid counterion is selected from the group consisting of pamoic acid, caproic acid, cypionic acid, decanoic acid, camphor sulfonic acid, enanthic acid, palmitic acid, fusidic acid, gluceptic acid, gluconic acid, lactobionic acid, lauric acid, levulinic acid and valeric acid, a process for the preparation and pharmaceutical composition comprising the same. Further, the invention relates to the use of said pharmaceutical composition comprising the acid addition salt of risperidone in the treatment of patient suffering from psychotic disorders.

The present invention relates to novel heterocycle-substituted diphosphonic acids, and the pharmaceutically-acceptable salts and esters thereof, in which the diphosphonate-substituted carbon atom moiety is attached to a carbon atom in a nitrogen-containing six membered ring heterocycle, preferably a piperidine ring. The heterocycle-substituted diphosphonic acid compounds have the general structure: ##STR1## wherein Z is a nitrogen-containing six membered ring heterocycle moiety selected from piperidinyl, diazinyl and triazinyl; m, n and m+n are from 0 to 10; Q is a covalent bond or a moiety selected from oxygen, sulfur or nitrogen; and R1, R2, R3 and R4 are substituent groups.The present invention further relates to pharmaceutical compositions containing these novel compounds. Finally this invention relates to methods for treating or preventing diseases characterized by abnormal calcium and phosphate metabolism by utilizing a compound or pharmaceutical composition of the present invention.

Antivirally active compounds of formula (I), wherein R1 is hydrogen, hydroxy, mercapto or amino; R2 is hydrogen, hydroxy, fluoro, chloro or amino; R3 and R4 are independently selected from (II), (III), amino, hydroxy or an ether or ester residue thereof, or R3 together with R4 is (IV), wherein M is hydrogen or a pharmaceutically acceptable counterion; and n is 1 or 2; with the proviso that, when R2 is amino and R3 and R4 are hydroxy, R1 is not hydroxy and in addition, when n=1, R1 is not hydrogen, and pharmaceutically acceptable salts thereof; processes for preparation of said compounds, a pharmaceutical composition comprising said compounds, methods for treatments of virus infections as well as use of compounds of formula (I) without the proviso for the manufacture of a medicament for treatment of AIDS. ##STR1##

Shape memory and pseudoelastic martensitic behavior is enabled by a structure in which there is provided a crystalline ceramic material that is capable of undergoing a reversible martensitic transformation and forming martensitic domains, during such martensitic transformation, that have an elongated domain length. The ceramic material is configured as a ceramic material structure including a structural feature that is smaller than the elongated domain length of the ceramic material.

The present invention provides a rubber composition that can enhance the fuel economy, wet-grip performance, and abrasion resistance in a balanced manner, and a pneumatic tire using this rubber composition. The present invention relates to a rubber composition that contains a rubber component, silica, and a silane coupling agent, wherein the rubber component contains, based on 100% by mass of the rubber component, not less than 5% by mass of a conjugated diene polymer containing a constituent unit based on a conjugated diene and a constituent unit represented by formula (I) below, at least one terminal of the polymer being modified with a specific compound; an amount of the silica is 5 to 150 parts by mass per 100 parts by mass of the rubber component; and the silane coupling agent contains a mercapto group.

The invention relates to a method of neutralizing paints, that includes adding at least one associative neutralizing agent to a formulation such as a pigment concentrate, a white paint base or paint. The associative neutralizing agent includes at least one neutralizing group N and at least one nitrogenous associative group A bonded together by at least one “spacer” group Sp. The invention also relates to pigment concentrates and to paints containing at least one such associative neutralizing agent.

The purpose of the present invention is to provide a rubber composition with which it is possible to produce a tire that retains wear resistance and has excellent frictional force on ice, and a pneumatic tire using the rubber composition. The rubber composition of the present invention is a rubber composition comprising a diene rubber, carbon black and/or a white filler, and a master batch prepared by premixing a non-diene rubber and an organic peroxide, wherein a total content of carbon black and white filler is from 20 to 70 parts by mass per 100 parts by mass of diene rubber and a content of the non-diene rubber in the master batch is from 3 to 30 parts by mass per 100 parts by mass of the diene rubber.

A logical operations functional block for an execution unit of a processor includes a first input data link for a first operand and a second input data link for a second operand. The execution unit includes a register connected to an error correction code detection unit. The logical operations functional block includes a look-up table configured to receive an error correction code syndrome from the error correction code detection unit. The logical operations functional block also includes a multiplexer configured to receive an output signal from the look-up table at a first input and the first operand at a second input, wherein an output of the multiplexer is coupled to the first input data link of a logical functional unit.

The present application is directed to a novel composition which acts as a barrier to noxious agents while adding self-detoxifying catalytic treatments to neutralize the noxious and harmful warfare agents when applied for example on a fabric, or other solid support.

An exemplary system for treatment and disposal of pharmaceutical waste comprises a sealable pail, a stirring device, a sealable bag, a container, an acidic substance, and a denaturant. The sealable pail receives the pharmaceutical waste and the acidic substance. The acidic substance dissolves the pharmaceutical waste, and the stirring device stirs the acidic substance to ensure that the pharmaceutical waste is completely dissolved. The denaturant is added to the dissolved pharmaceutical waste and renders the dissolved pharmaceutical waste safe for transport. The treated pharmaceutical waste is sealed within the sealable pail, and the sealable bag receives the sealed pail and is sealed. The sealed bag is then placed in the container for transport to a disposal facility.

Containers and methods for disposing unused pharmaceutical product are disclosed. Each container (100, 200, 300) may include a container body (104, 204, 304) with an internal chamber (116, 216, 316) for storing pharmaceutical product, along with a cover (124, 224, 324) for selectively limiting access to the chamber (116, 216, 316). An encapsulation component (128, 228, 328) may be selectively disposable within the chamber (116, 216, 316), and may be operable to encapsulate the pharmaceutical product within the container (100, 200, 300). For instance, the encapsulation component (128, 228, 328) may melt and/or flow into contact with the pharmaceutical product and thereafter solidify to encapsulate the pharmaceutical product. The encapsulation component (128, 228, 328) may melt and thereafter solidify between the cover (124, 224, 324) and shell (104, 204, 304) to limit removal of the cover (124, 224, 324) from the shell (104, 204, 304).

A circuit arrangement and method couple a hardware-based pseudorandom number generator (PRNG) to an execution unit in such a manner that pseudorandom numbers generated by the PRNG may be selectively output to the execution unit for use as an operand during the execution of instructions by the execution unit. A PRNG may be coupled to an input of an operand multiplexer that outputs to an operand input of an execution unit so that operands provided by instructions supplied to the execution unit are selectively overridden with pseudorandom numbers generated by the PRNG. Furthermore, overridden operands provided by instructions supplied to the execution unit may be used as seed values for the PRNG.

A method for generating multi-level (or multi-bit) pseudo-random sequences is disclosed. This embodiment relates to communication systems, and more particularly to generating multi-level pseudo random symbol sequence. Present day systems do not employ effective mechanisms for generation of multi level PRBS in order to increase the data communication rates. Further, these systems do not cover all the possible transitions for the outputs of the system. The proposed system employs mechanisms in order to generate PRBS signals for producing multi levels signals to the electronic components. The mechanism employs alternate bit tapping techniques. In the alternate bit tapping technique, bits are tapped alternatively to determine the current state and the next state of the system. In addition, the mechanism also covers all the possible states of the output vector with transitions between the output states. This ensures that high data rates are obtained for a given bandwidth of operation.

A method for efficient dispatch/completion of a work element within a multi-node data processing system. The method comprises: selecting specific processing units from among the processing nodes to complete execution of a work element that has multiple individual work items that may be independently executed by different ones of the processing units; generating an allocated processor unit (APU) bit mask that identifies at least one of the processing units that has been selected; placing the work element in a first entry of a global command queue (GCQ); associating the APU mask with the work element in the GCQ; and responsive to receipt at the GCQ of work requests from each of the multiple processing nodes or the processing units, enabling only the selected specific ones of the processing nodes or the processing units to be able to retrieve work from the work element in the GCQ.

A processing apparatus includes an execution unit which performs computation on two operand inputs each being selectable between read data from a register and an immediate value. The processing apparatus also includes another execution unit which performs computation on two operand inputs, one of which is selectable between read data from a register and an immediate value, and the other of which is an immediate value. A control unit determines, based on a received instruction specifying a computation on two operands, whether each of the two operands specifies read data from a register or an immediate value. Depending on the determination result, the control unit causes one of the execution units to execute the computation specified by the received instruction.

Compositions and methods for improved cleaning using neutral cleaners are disclosed. In particular, neutral pH cleaning compositions according to the invention employ a synergistic combination of water insoluble surfactants and an anionic hydrotropes capable of forming a stable, low-foaming solution. The neutral cleaning solutions provide significant benefits over water insoluble microemulsions traditionally used for neutral cleaning compositions and provide at least equivalent cleaning efficacy as non-neutral cleaning compositions.

A pharmaceutical composition comprising lectins is anti-tumorigenic and anti-viral, bacterial or protozoan. The composition, termed BiOmune is also useful for imaging, diagnosis and therapy of cancer.

The present invention relates to oligomer compounds (oligomers) for the treatment and prevention of acute myeloid leukemia, which target GLI2 mRNA in a cell, leading to reduced expression of GLI2.

An integrated-circuit memory controller outputs to a memory device a first signal in a first state to enable operation of synchronous data transmission and reception circuits within the memory device. A transaction queue within the memory controller stores memory read and write requests that, to be serviced, require operation of the synchronous data transmission and reception circuits, respectively, within the memory device. Power control circuitry within the memory controller determines that the transaction queue has reached a predetermined state and, in response, outputs the first signal to the memory device in a second state to disable operation of the synchronous data transmission and reception circuits within the memory device.

A reusable needle guide suitable for an ultrasonic probe to be use for an endocavity examination of a patient is disclosed. The needle guide basically comprises at least a first and second guide members and a mounting (e.g., clamp) assembly. The clamp assembly serves to releasably mount the needle guide on the probe. The first guide member has a first passageway-forming surface. The second guide member has a second passageway-forming surface. The guide members are connected together to enable them to be pivoted from a closed orientation to an open orientation and vice versa. The first and second passageway-forming surfaces form an elongated passageway to guide a needle therethrough when in the closed orientation. The first and second passageway-forming surfaces are disposed at an angle to each other when they are in the open orientation, whereupon the first and second passageway-forming surfaces can be readily cleaned.

The subject of the present invention are novel esters of (acyloxymethyl)acrylamide, a pharmaceutical composition containing them and their use in the production of drugs for the prophylaxis or treatment of oncogenic diseases and diseases connected with increased cell proliferation.

A phenyl alkyl carbamate derivative compound and a pharmaceutical composition containing the compound are provided. More specifically, the phenyl alkyl carbamate derivative compound and a pharmaceutically acceptable salt thereof, a composition for muscle relaxation containing the phenyl alkyl carbamate derivative compounds and/or pharmaceutically acceptable salt thereof as an active ingredient, and a method of muscle relaxation comprising administering a pharmaceutically effective amount of the phenyl alkyl carbamate derivative compound and/or a pharmaceutically acceptable salt thereof to a subject in need of to a subject in need of, are provided.