The document discusses various machine learning clustering algorithms like K-means clustering, DBSCAN, and EM clustering. It also discusses neural network architectures like LSTM, bi-LSTM, and convolutional neural networks. Finally, it presents results from evaluating different chatbot models on various metrics like validation score.
"손코딩뇌컴파일눈디버깅" 모임을 소개합니다.
백문이 불여일런, 트라이얼앤에러(Trial and Error) 식의 몹쓸 교육을 받아 온 개발자들이 코딩하기 전에 신중하고 꼼꼼하게 생각해보기란 쉽지 않습니다.
개발 시간 중 디버깅 시간이 절반 이상을 차지하고 있는 실정에 버그를 줄이기 위해 TDD니 유닛테스트니 많은 방법들이 개발되고 있지만 가장 일차적으로 중요한 것은 개발자들이 꼼꼼히 따져보는 것이 아니겠는지요?
미국의 선진 SW회사들은 이미 화이트보드에 PS문제를 푸는 것을 인터뷰 방식으로 채택하고 있습니다. 이는 이와 같은 풀이 방식이 개발자들의 기본 역량을 측정하기에 알맞은 지표라는 것이고, 개발자들이 기본적으로 갖춰야 할 역량이기도 하다는 것 입니다.
또한 자신의 생각을 명확하게 정리하고 다른 사람이 이해할 수 있도록 전달하는 Communication Skill 도 개발자가 갖춰야 할 역량 중 하나 입니다. 알고리즘을 어떻게 구현할 것인가를 팀원들과 소통하면서 자연스럽게 생각을 정리하고 전달하는 연습도 할 수 있습니다.
컴퓨터에 앉아 코딩하기 전 펜과 종이를 들고 눈과 머리와 손을 굴려 보시는 것은 어떠신지요??
Python과 Tensorflow를 활용한 AI Chatbot 개발 및 실무 적용Susang Kim
도입
AI Chatbot 소개
Chatbot Ecosystem
Closed vs Open Domain
Rule Based vs AI
Chat IF Flow and Story Slot
AI기반의 학습을 위한 Data 구성 방법
Data를 구하는 법 / Train을 위한 Word Representation
Data의 구성 / Data Augmentation(Intent, NER)
자연어처리 위한 AI 적용 방안
Intent (Char-CNN) / QnA (Seq2Seq)
Named Entity Recognition (Bi-LSTM CRF) / Ontology (Graph DB)
Chatbot Service를 위한 Architecture 구성
Chatbot Architecture
NLP Architecture
Web Service Architecture
Bot builder / Chatbot API
Test Codes for Chatbot
실무에서 발생하는 문제와 해결 Tips
Ensemble and voting / Trigger / Synonym(N-Gram)
Tone Generator / Parallel processing / Response Speed
마무리
[설명 코드]
Text Augmentation / Slot Bot / QA Bot / Graph DB / Response Generator
책 읽어주는 딥러닝: 배우 유인나가 해리포터를 읽어준다면 DEVIEW 2017Taehoon Kim
발표 영상 : https://youtu.be/klnfWhPGPRs
코드 : https://github.com/carpedm20/multi-speaker-tacotron-tensorflow
음성 합성 데모 : http://carpedm20.github.io/tacotron
발표 소개 : https://deview.kr/2017/schedule/182
딥러닝을 활용한 음성 합성 기술을 소개하고 개발 경험과 그 과정에서 얻었던 팁을 공유하고자 합니다.
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [Secret X 팀] : XAI를 활용한 수능 영어영역 문제풀이BOAZ Bigdata
데이터 분석 프로젝트를 진행한 Secret X 팀에서는 아래와 같은 프로젝트를 진행했습니다.
비밀집단에서는 영어 문제를 풀고 XAI를 이용해 이를 해설합니다.
17기 권강미 연세대학교 문헌정보학과
17기 김지수 고려대학교 통계학과
17기 이수경 성균관대학교 데이터사이언스전공
제 15회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [YouPlace 팀] : 카프카와 스파크를 활용한 유튜브 영상 속 제주 명소 검색 BOAZ Bigdata
데이터 엔지니어링 프로젝트를 진행한 YouPlace팀에서는 아래와 같은 프로젝트를 진행했습니다.
<aside>
이젠 검색도 유튜브 시대
제주여행을 계획할 때 브이로그 영상을 많이 참고하실텐데요
수많은 영상들과 영상 속 분산된 명소들을 하나 하나 찾으려 생각하면 막막하지 않으셨나요?
이러한 고민을 갖고 계신 분들을 위해, 유튜브 브이로거들이 찾아간 여행 명소들을 지도에서 한 눈에 파악할 수 있도록 만들었어요
(github : https://github.com/Boaz-Youplace)
16기 엔지니어링 고은서 | 중앙대학교 소프트웨어학부
16기 엔지니어링 류정화 | 성신여자대학교 융합보안공학과
16기 엔지니어링 송경민 | 국민대학교 소프트웨어학과
BigQuery의 모든 것(기획자, 마케터, 신입 데이터 분석가를 위한) 입문편Seongyun Byeon
The document contains log data from user activities on a platform. There are three columns - user_id, event, and event_date. It logs the activities of 5 users over several days, including events like logins, posts, comments, views. It also includes some aggregated data on unique events and totals by user.
제 17회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [Catch, Traffic!] : 지하철 혼잡도 및 키워드 분석 데이터 파이프라인 구축BOAZ Bigdata
데이터 엔지니어링 프로젝트를 진행한 Catch, Traffic! 팀에서는 아래와 같은 프로젝트를 진행했습니다.
수도권 교통의 혼잡성을 해결하기 위한 방안을 찾는 데이터 파이프라인 구축
18기 김인섭 숭실대학교 산업정보시스템공학과
18기 김재민 국민대학교 AI빅데이터융합경영학과
18기 서은유 동덕여자대학교 정보통계학과
18기 윤정원 숙명여자대학교 소프트웨어융합전공
18기 이현진 서울과학기술대학교 산업정보시스템전공
18기 조은학 명지대학교 융합소프트웨어학부
[야생의 땅: 듀랑고] 서버 아키텍처 - SPOF 없는 분산 MMORPG 서버Heungsub Lee
NDC14에서 발표한 "[야생의 땅: 듀랑고] 서버 아키텍처" 세션의 슬라이드입니다.
슬라이드에 설명이 많지 않은데, 디스이즈게임에서 발표 내용을 잘 정리해주었습니다. 기사도 함께 보시면 좋을 것 같습니다.
http://www.thisisgame.com/webzine/news/nboard/4/?n=54955
This document discusses techniques for recommender systems including multi-armed bandit (MAB), Thompson sampling, user clustering, and using item features. It provides examples of how MAB works using the ε-greedy approach and explores the tradeoff between exploration and exploitation. User clustering is presented as a way to group users based on click-through rate to improve targeting. Finally, it suggests using different item features like images, text, and collaborative filtering data as inputs to recommendation models.
This document discusses starting a mobile app development company. It provides details on the company's founding in 2015, services offered such as mobile app development and information technology consulting. It also includes charts showing the company's growth, with revenue increasing from KRW 17,500 in January 2016 to KRW 62,000 by September 2017 as the number of employees grew from 2 to 15 over the same period. The document advocates that the company will continue achieving growth and success by focusing on customer satisfaction.
This document provides an introduction and overview of Cassandra and NoSQL databases. It discusses the challenges faced by modern web applications that led to the development of NoSQL databases. It then describes Cassandra's data model, API, consistency model, and architecture including write path, read path, compactions, and more. Key features of Cassandra like tunable consistency levels and high availability are also highlighted.
NoSQL - MongoDB. Agility, scalability, performance. I am going to talk about the basis of NoSQL and MongoDB. Why some projects requires RDBMs and another NoSQL databases? What are the pros and cons to use NoSQL vs. SQL? How data are stored and transefed in MongoDB? What query language is used? How MongoDB supports high availability and automatic failover with the help of the replication? What is sharding and how it helps to support scalability?. The newest level of the concurrency - collection-level and document-level.
Reed Solomon codes are a type of linear block code that can detect and correct errors in transmitted data. Reed Solomon codes operate by dividing a message into blocks, calculating redundant parity data for each block based on the message contents, and transmitting the blocks with parity. At the receiver, the redundant data enables detection and correction of errors that may have occurred during transmission. Popular examples include RS(255,223) codes that can correct up to 16 byte errors per codeword. Reed Solomon codes are widely used in storage devices and wireless communications due to their high error correction capability.
Keynote: Machine Learning for Design Automation at DAC 2018Manish Pandey
Manish Pandey gave a keynote talk on transforming EDA with machine learning and discussed opportunities and challenges. He described how machine learning can be applied across different design abstraction levels from formal verification to silicon engineering. Pandey also discussed using machine learning techniques like reinforcement learning and word embeddings to optimize formal verification, simulation, and mask synthesis. Finally, he outlined challenges with data availability and model development for machine learning in EDA.
An efficient reconfigurable code rate cooperative low-density parity check co...IJECEIAES
In recent days, extensive digital communication process has been performed. Due to this phenomenon, a proper maintenance of authentication, communication without any overhead such as signal attenuation code rate fluctuations during digital communication process can be minimized and optimized by adopting parallel encoder and decoder operations. To overcome the above-mentioned drawbacks by using proposed reconfigurable code rate cooperative (RCRC) and low-density parity check (LDPC) method. The proposed RCRC-LDPC is capable to operate over gigabits/sec data and it effectively performs linear encoding, dual diagonal form, widens the range of code rate and optimal degree distribution of LDPC mother code. The proposed method optimize the transmission rate and it is capable to operate on 0.98 code rate. It is the highest upper bounded code rate as compared to the existing methods. The proposed method optimizes the transmission rate and is capable to operate on a 0.98 code rate. It is the highest upper bounded code rate as compared to the existing methods. the proposed method's implementation has been carried out using MATLAB and as per the simulation result, the proposed method is capable of reaching a throughput efficiency greater than 8.2 (1.9) gigabits per second with a clock frequency of 160 MHz.
LDPC Encoding and Hamming Encoding using MATLAB.
An LDPC code is a linear block code characterised by a very sparse parity-check matrix. This means that the parity check matrix has a very low concentration of 1’s in it, hence the name is “low-density parity-check” code. The sparseness of LDPC codes is what as it can lead to excellent performance in terms of bit error rates.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
EIGRP is a Cisco proprietary distance vector routing protocol that uses the Diffusing Update Algorithm (DUAL) to determine the best route to a destination. It has an administrative distance of 90 internally and 170 externally and uses a composite metric that factors bandwidth, delay, reliability, load and MTU to calculate the best path. EIGRP configuration involves enabling the protocol on interfaces and networks, tuning metric weights, summarization, authentication, and timers. Troubleshooting commands display interface, neighbor, topology and traffic information to identify issues.
The document discusses the simulation of a Triple Data Encryption Standard (Triple DES) circuit using VHDL. It provides background on Triple DES, describes the design and structure of the Triple DES circuit in VHDL, and presents the results of testing the encryption and decryption functions of the circuit through simulation. Testing showed the circuit correctly performed encryption and decryption on input data using the Triple DES algorithm. The design utilized some FPGA resources but would require a clock generator and RAM for implementation on an actual FPGA board.
New Technique Using Multiple Symmetric keys for Multilevel EncryptionIJERA Editor
In a world of accelerating communications, cryptography has become an essential component of the modern
means of communication systems. The emergence of the webas a reliable medium for commerce and
communication has made cryptography an essential component. Many algorithms or ciphers are in use
nowadays. The quality of the cipher is judged byits ability to prevent an unrelated party fromknowingthe
original content of the encrypted message. The proposed “Multilevel Encryption Model” is a cryptosystem that
adopts the basic principles of cryptography. It uses five symmetric keys (multiple)
in floating point numbers, plaintext, substitution techniques and key combinations with unintelligible
sequence to produce the ciphertext. The decryption process is also designed to reproduce the plaintext
This document discusses error detection and correction techniques for digital communication and storage. It covers basic detection methods like parity and checksums. It then discusses more advanced error correction codes like Hamming codes, which can detect and correct single bit errors. Reed-Solomon codes are also covered, which can detect and correct multiple symbol errors and are used in applications like CDs and DVDs. Logic implementations for Hamming encoders, decoders and Reed-Solomon encoders are shown at a high level.
High Secure Password Authentication SystemAkhil Nadh PC
Muti Server Password Authentication system. Split the password and store it in multiple server for increasing the degree of security of the data. The technique is used in storing the login information securely
1) The document discusses several Java performance myths and uses microbenchmarks to analyze them. It finds that final variables and String concatenation are not necessarily faster than alternatives.
2) It recommends using the Caliper framework for robust microbenchmarking and provides several useful JVM flags for profiling and optimization.
3) The document outlines various Java optimization strategies used by the JVM compiler including inlining, intrinsics, escape analysis, and loop unrolling. It emphasizes the importance of clear and readable code over premature optimization.
Explores common patterns in microservice architectures and how these are addressed in the gilmour library.
Discusses async signal-slot as well as synchronous request-response architectures.
Introduces unix inspired composition of microservices for more modular and flexible design.
This document provides a sample MATLAB code for implementing an MB-OFDM transmission block according to the ECMA-368 standard. The code takes in a random binary source, scrambles it, performs convolutional encoding and puncturing, and then does three stages of interleaving - symbol, tone, and cyclic interleaving. The interleaved data is then QPSK modulated, has guard and pilot carriers added, undergoes 128-point IFFT, and is transmitted as the baseband signal. A plot of the transmitted signal is also shown.
The document discusses code generation techniques in compiler construction. It describes generating executable code from source code by using intermediate representations like three-address code and P-code. It covers generating code from syntax trees, implementing intermediate codes using data structures, and translating between different intermediate representations and target machine code.
07 140430-ipp-languages used in llvm during compilationAdam Husár
The document describes the languages and representations used at each stage of compilation in LLVM. It discusses how the C/C++ frontend transforms source code into an AST then LLVM IR. The optimizer performs optimizations on the LLVM IR. The backend lowers the LLVM IR into a selection DAG with machine instructions and finally emits assembly code. The compilation process translates from the original high-level language into target-specific assembly.
The document discusses locally decodable codes, which allow recovery of individual data symbols from a coded data set even after erasures. Reed-Muller codes and multiplicity codes were early constructions that provided locality but only up to a rate of 0.5. Matching vector codes were later introduced and can achieve locality r for codes of positive rate and length n=O(r^2). However, the optimal tradeoff between rate, length, and locality remains an open problem.
The document discusses challenges with using reinforcement learning for robotics. While simulations allow fast training of agents, there is often a "reality gap" when transferring learning to real robots. Other approaches like imitation learning and self-supervised learning can be safer alternatives that don't require trial-and-error. To better apply reinforcement learning, robots may need model-based approaches that learn forward models of the world, as well as techniques like active localization that allow robots to gather targeted information through interactive perception. Closing the reality gap will require finding ways to better match simulations to reality or allow robots to learn from real-world experiences.
[243] Deep Learning to help student’s Deep LearningNAVER D2
This document describes research on using deep learning to predict student performance in massive open online courses (MOOCs). It introduces GritNet, a model that takes raw student activity data as input and predicts outcomes like course graduation without feature engineering. GritNet outperforms baselines by more than 5% in predicting graduation. The document also describes how GritNet can be adapted in an unsupervised way to new courses using pseudo-labels, improving predictions in the first few weeks. Overall, GritNet is presented as the state-of-the-art for student prediction and can be transferred across courses without labels.
[234]Fast & Accurate Data Annotation Pipeline for AI applicationsNAVER D2
This document provides a summary of new datasets and papers related to computer vision tasks including object detection, image matting, person pose estimation, pedestrian detection, and person instance segmentation. A total of 8 papers and their associated datasets are listed with brief descriptions of the core contributions or techniques developed in each.
[226]NAVER 광고 deep click prediction: 모델링부터 서빙까지NAVER D2
This document presents a formula for calculating the loss function J(θ) in machine learning models. The formula averages the negative log likelihood of the predicted probabilities being correct over all samples S, and includes a regularization term λ that penalizes predicted embeddings being dissimilar from actual embeddings. It also defines the cosine similarity term used in the regularization.
[214] Ai Serving Platform: 하루 수 억 건의 인퍼런스를 처리하기 위한 고군분투기NAVER D2
The document discusses running a TensorFlow Serving (TFS) container using Docker. It shows commands to:
1. Pull the TFS Docker image from a repository
2. Define a script to configure and run the TFS container, specifying the model path, name, and port mapping
3. Run the script to start the TFS container exposing port 13377
The document discusses linear algebra concepts including:
- Representing a system of linear equations as a matrix equation Ax = b where A is a coefficient matrix, x is a vector of unknowns, and b is a vector of constants.
- Solving for the vector x that satisfies the matrix equation using linear algebra techniques such as row reduction.
- Examples of matrix equations and their component vectors are shown.
This document describes the steps to convert a TensorFlow model to a TensorRT engine for inference. It includes steps to parse the model, optimize it, generate a runtime engine, serialize and deserialize the engine, as well as perform inference using the engine. It also provides code snippets for a PReLU plugin implementation in C++.
The document discusses machine reading comprehension (MRC) techniques for question answering (QA) systems, comparing search-based and natural language processing (NLP)-based approaches. It covers key milestones in the development of extractive QA models using NLP, from early sentence-level models to current state-of-the-art techniques like cross-attention, self-attention, and transfer learning. It notes the speed and scalability benefits of combining search and reading methods for QA.
Sustainability requires ingenuity and stewardship. Did you know Pigging Solutions pigging systems help you achieve your sustainable manufacturing goals AND provide rapid return on investment.
How? Our systems recover over 99% of product in transfer piping. Recovering trapped product from transfer lines that would otherwise become flush-waste, means you can increase batch yields and eliminate flush waste. From raw materials to finished product, if you can pump it, we can pig it.
Kief Morris rethinks the infrastructure code delivery lifecycle, advocating for a shift towards composable infrastructure systems. We should shift to designing around deployable components rather than code modules, use more useful levels of abstraction, and drive design and deployment from applications rather than bottom-up, monolithic architecture and delivery.
7 Most Powerful Solar Storms in the History of Earth.pdfEnterprise Wired
Solar Storms (Geo Magnetic Storms) are the motion of accelerated charged particles in the solar environment with high velocities due to the coronal mass ejection (CME).
RPA In Healthcare Benefits, Use Case, Trend And Challenges 2024.pptxSynapseIndia
Your comprehensive guide to RPA in healthcare for 2024. Explore the benefits, use cases, and emerging trends of robotic process automation. Understand the challenges and prepare for the future of healthcare automation
Coordinate Systems in FME 101 - Webinar SlidesSafe Software
If you’ve ever had to analyze a map or GPS data, chances are you’ve encountered and even worked with coordinate systems. As historical data continually updates through GPS, understanding coordinate systems is increasingly crucial. However, not everyone knows why they exist or how to effectively use them for data-driven insights.
During this webinar, you’ll learn exactly what coordinate systems are and how you can use FME to maintain and transform your data’s coordinate systems in an easy-to-digest way, accurately representing the geographical space that it exists within. During this webinar, you will have the chance to:
- Enhance Your Understanding: Gain a clear overview of what coordinate systems are and their value
- Learn Practical Applications: Why we need datams and projections, plus units between coordinate systems
- Maximize with FME: Understand how FME handles coordinate systems, including a brief summary of the 3 main reprojectors
- Custom Coordinate Systems: Learn how to work with FME and coordinate systems beyond what is natively supported
- Look Ahead: Gain insights into where FME is headed with coordinate systems in the future
Don’t miss the opportunity to improve the value you receive from your coordinate system data, ultimately allowing you to streamline your data analysis and maximize your time. See you there!
Advanced Techniques for Cyber Security Analysis and Anomaly DetectionBert Blevins
Cybersecurity is a major concern in today's connected digital world. Threats to organizations are constantly evolving and have the potential to compromise sensitive information, disrupt operations, and lead to significant financial losses. Traditional cybersecurity techniques often fall short against modern attackers. Therefore, advanced techniques for cyber security analysis and anomaly detection are essential for protecting digital assets. This blog explores these cutting-edge methods, providing a comprehensive overview of their application and importance.
Fluttercon 2024: Showing that you care about security - OpenSSF Scorecards fo...Chris Swan
Have you noticed the OpenSSF Scorecard badges on the official Dart and Flutter repos? It's Google's way of showing that they care about security. Practices such as pinning dependencies, branch protection, required reviews, continuous integration tests etc. are measured to provide a score and accompanying badge.
You can do the same for your projects, and this presentation will show you how, with an emphasis on the unique challenges that come up when working with Dart and Flutter.
The session will provide a walkthrough of the steps involved in securing a first repository, and then what it takes to repeat that process across an organization with multiple repos. It will also look at the ongoing maintenance involved once scorecards have been implemented, and how aspects of that maintenance can be better automated to minimize toil.
Comparison Table of DiskWarrior Alternatives.pdfAndrey Yasko
To help you choose the best DiskWarrior alternative, we've compiled a comparison table summarizing the features, pros, cons, and pricing of six alternatives.
An invited talk given by Mark Billinghurst on Research Directions for Cross Reality Interfaces. This was given on July 2nd 2024 as part of the 2024 Summer School on Cross Reality in Hagenberg, Austria (July 1st - 7th)
The Rise of Supernetwork Data Intensive ComputingLarry Smarr
Invited Remote Lecture to SC21
The International Conference for High Performance Computing, Networking, Storage, and Analysis
St. Louis, Missouri
November 18, 2021
The DealBook is our annual overview of the Ukrainian tech investment industry. This edition comprehensively covers the full year 2023 and the first deals of 2024.
Are you interested in dipping your toes in the cloud native observability waters, but as an engineer you are not sure where to get started with tracing problems through your microservices and application landscapes on Kubernetes? Then this is the session for you, where we take you on your first steps in an active open-source project that offers a buffet of languages, challenges, and opportunities for getting started with telemetry data.
The project is called openTelemetry, but before diving into the specifics, we’ll start with de-mystifying key concepts and terms such as observability, telemetry, instrumentation, cardinality, percentile to lay a foundation. After understanding the nuts and bolts of observability and distributed traces, we’ll explore the openTelemetry community; its Special Interest Groups (SIGs), repositories, and how to become not only an end-user, but possibly a contributor.We will wrap up with an overview of the components in this project, such as the Collector, the OpenTelemetry protocol (OTLP), its APIs, and its SDKs.
Attendees will leave with an understanding of key observability concepts, become grounded in distributed tracing terminology, be aware of the components of openTelemetry, and know how to take their first steps to an open-source contribution!
Key Takeaways: Open source, vendor neutral instrumentation is an exciting new reality as the industry standardizes on openTelemetry for observability. OpenTelemetry is on a mission to enable effective observability by making high-quality, portable telemetry ubiquitous. The world of observability and monitoring today has a steep learning curve and in order to achieve ubiquity, the project would benefit from growing our contributor community.
Mitigating the Impact of State Management in Cloud Stream Processing SystemsScyllaDB
Stream processing is a crucial component of modern data infrastructure, but constructing an efficient and scalable stream processing system can be challenging. Decoupling compute and storage architecture has emerged as an effective solution to these challenges, but it can introduce high latency issues, especially when dealing with complex continuous queries that necessitate managing extra-large internal states.
In this talk, we focus on addressing the high latency issues associated with S3 storage in stream processing systems that employ a decoupled compute and storage architecture. We delve into the root causes of latency in this context and explore various techniques to minimize the impact of S3 latency on stream processing performance. Our proposed approach is to implement a tiered storage mechanism that leverages a blend of high-performance and low-cost storage tiers to reduce data movement between the compute and storage layers while maintaining efficient processing.
Throughout the talk, we will present experimental results that demonstrate the effectiveness of our approach in mitigating the impact of S3 latency on stream processing. By the end of the talk, attendees will have gained insights into how to optimize their stream processing systems for reduced latency and improved cost-efficiency.
Blockchain technology is transforming industries and reshaping the way we conduct business, manage data, and secure transactions. Whether you're new to blockchain or looking to deepen your knowledge, our guidebook, "Blockchain for Dummies", is your ultimate resource.
29. POS정보Token Index EOMI 정보
[밥 을 먹다] [N, JOSA, VERB] [0, 0, 다]
∑
Hidde
n=128
Token one-hot
d=# of vocabulary
POS tag one-hot
d=# of tag
Token endingone-hot
d=# of ending
Token
EmbeddingMatrix
POS tag
EmbeddingMatrix
Token ending
EmbeddingMatrix
31. Chatbot Builder
Chatbot Engine
Chatbot Service Serving
Deep Learning
Application
Resource
Manager
Node
Manager
Node
Manager
Node
Manager
Docker
RegistryZoo keeper
Training Data
Pre-Processing
…
Multi model
version management
and deploy