The document discusses graph databases and their properties. Graph databases are structured to store graph-based data by using nodes and edges to represent entities and their relationships. They are well-suited for applications with complex relationships between entities that can be modeled as graphs, such as social networks. Key graph database technologies mentioned include Neo4j, OrientDB, and TinkerPop which provides graph traversal capabilities.
The document discusses graph databases and their properties. Graph databases are structured to store graph-based data by using nodes and edges to represent entities and their relationships. They are well-suited for applications with complex relationships between entities that can be modeled as graphs, such as social networks. Key graph database technologies mentioned include Neo4j, OrientDB, and TinkerPop which provides graph traversal capabilities.
The document discusses attention mechanisms and their implementation in TensorFlow. It begins with an overview of attention mechanisms and their use in neural machine translation. It then reviews the code implementation of an attention mechanism for neural machine translation from English to French using TensorFlow. Finally, it briefly discusses pointer networks, an attention mechanism variant, and code implementation of pointer networks for solving sorting problems.
DE-CPS 2017 The INTO-CPS Cyber-Physical System Profile Alessandra BagnatoAlessandra Bagnato
?
The document summarizes the INTO-CPS (INtegrated TOolchain for Cyber-Physical Systems) profile, which specializes the SysML block concept into components for modeling cyber-physical systems. It describes an example using the three-tank water tank system to demonstrate the profile. The profile identifies two diagram types - architectural structure diagrams and connection diagrams. It also lists industrial partners collaborating on the project and plans for a summer school on CPS modeling.
The document discusses various methods to reduce cogging torque in permanent magnet machines. Cogging torque is an undesirable torque pulsation caused by the interaction between permanent magnets and stator slots. Several techniques are presented: shaping magnets, lengthening the air gap, adding auxiliary grooves on magnets, skewing the rotor or stator, using slotless stators, asymmetrical magnet arrangements, changing the number of stator slots, skewing stator teeth, and shifting magnets axially. These techniques reduce cogging torque by 16-58% but also reduce the overall torque output in some cases. Slotless stators, bread loaf magnets, and using an odd number of stator slots are shown to
The document provides tips for developing Korean chatbots, including discussing chatbot goals, architectures, data collection, natural language processing tools, and machine learning algorithms. It recommends focusing chatbots for business on a small number of important intents, using a modular architecture for easier debugging, and training natural language tools on domain-specific data collected from sources like web scraping.
100% Serverless big data scale production Deep Learning Systemhoondong kim
?
- BigData Sale Deep Learning Training System (with GPU Docker PaaS on Azure Batch AI)
- Deep Learning Serving Layer (with Auto Scale Out Mode on Web App for Linux Docker)
- BigDL, Keras, Tensorlfow, Horovod, TensorflowOnAzure
ChatGPT is a natural language processing technology developed by OpenAI. This model is based on the GPT-3 architecture and can be applied to various language tasks by training on large-scale datasets. When applied to a search engine, ChatGPT enables the implementation of an AI-based conversational system that understands user questions or queries and provides relevant information.
ChatGPT takes user questions as input and generates appropriate responses based on them. Since this model considers the context of previous conversations, it can provide more natural dialogue. Moreover, ChatGPT has been trained on diverse information from the internet, allowing it to provide practical and accurate answers to user questions.
When applying ChatGPT to a search engine, the system searches for relevant information based on the user's search query and uses ChatGPT to generate answers to present along with the search results. To do this, the search engine provides an interface that connects with ChatGPT, allowing the user's questions to be passed to the model and the answers generated by the model to be presented alongside the search results.
[Paper] Multiscale Vision Transformers(MVit)Susang Kim
?
This document summarizes research on multiscale vision transformers (MViT). MViT builds on the transformer architecture by incorporating a multiscale pyramid of features, with early layers operating at high resolution to model low-level visual information and deeper layers focusing on coarse, complex features. MViT introduces multi-head pooling attention to operate at changing resolutions, and uses separate spatial and temporal embeddings. Experiments on Kinetics-400 and ImageNet show MViT achieves better accuracy than ViT baselines with fewer parameters and lower computational cost. Ablation studies validate design choices in MViT like input sampling and stage distribution.
[Paper] dynamic routing between capsulesSusang Kim
?
Hinton ???? Google Brain? ???? ??
(NIPS 2017 ??)
CNN? ??? ?? ???? ???? Capsule? ?? ??? Feature Extraction? ??
(Pose, Speed, Light, Angle¡.)
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part.
[Paper] anti spoofing for face recognitionSusang Kim
?
This document summarizes a research paper on face anti-spoofing using deep learning models. It discusses using auxiliary supervision from additional data sources like depth maps and remote photoplethysmography (rPPG) signals to improve spoof detection performance. The proposed method uses a CNN to extract image features and an RNN to model rPPG signals. It evaluates the approach on the Spoof in the Wild database containing live and spoof videos, and compares error rates to other databases. The document provides background on anti-spoofing, defines relevant terms like rPPG and error metrics, and references related works and datasets.
DetectoRS for Object Detection/Segmentation
On COCO test-dev, DetectoRS achieves state-of-the art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation.
(2020.07)
The document summarizes the GroupFace face recognition method. GroupFace learns latent groups within training data and constructs group-based representations to enrich face embeddings. This helps narrow the search space for face matching compared to instance-only methods. GroupFace achieves state-of-the-art results on face verification and identification benchmarks by learning a joint group-aware representation through self-distributed grouping and an arcface-based loss. Ablation studies validate the importance of uniform group distributions and combining instance and group representations.
The document discusses a lecture on developing an AI chatbot using Python and TensorFlow, covering setting up a Docker environment, explaining example code in Jupyter notebooks, and introducing the two speakers and their backgrounds working on machine learning and chatbots.
3. I am Susang Kim as a developer
?Chatbot Develover
- Released in POSCO (Find people using by NLP/AI)
- Deep Learning MSA (ML,DNN, CNN, RNN)
?Agile Develover (Experienced in Pivotal Labs)
- TDD, CI, Pair programming, User Story
?iOS Develover (Ranked App store in 100th - 2011 Korea)
?Front-End Developer (React, D3, Typescript and ES6)
?POSCO MES ... (working at POSCO ICT for 10 year)
4. Contents
1. ??
2. AI Chatbot ??
Chatbot Ecosystem
Closed vs Open Domain
Rule Based vs AI
Chat IF Flow and Story Slot
3. AI??? ??? ?? Data ?? ??
Data? ??? ? / Train? ?? Word Representation
Data? ?? / Data Augmentation(Intent, NER)
4. ????? ?? AI ?? ??
Intent (Char-CNN) / QnA (Seq2Seq)
Named Entity Recognition (Bi-LSTM CRF) / Ontology (Graph DB)
5. Contents
6. Chatbot Service? ?? Architecture ??
Chatbot Architecture
NLP Architecture
Web Service Architecture
Bot builder / Chatbot API
Test Codes for Chatbot
7. ???? ???? ??? ?? Tips
Ensemble and voting / Trigger / Synonym(N-Gram)
Tone Generator / Parallel processing / Response Speed
8. ???
[?? ??]
Text Augmentation / Char-CNN / NER /Slot Bot / QA Bot / Graph DB / Response Generator
14. Closed Domain vs Open Domain
Rule Based
General
(abstract)
Open
Closed
Retrieval
(accuracy)
Impossible Strong AI
Weak AI
level of difficulty
?? Biz ????? ???? ???? ???? ?? Biz? ???? ??
15. Rule Based vs AI
Computer
Input
Program
Output
Rule
??, ??, ?? ???? ??? rule? ??????
- ???? ???? ?? ??? ? ????
Computer
Input
Output
Program
AI
???? Data??? ??? ?? ? ?? ??? ?? ? ??
- ??? Data?? ????(W2V,GloVe)
intent = ??? ???? ??? ??? => Intent : ?? ?? ?? ???
NER = ??? ???? ??? ??? => B-Loc O O B-Name O
??? ???
?? ? ???
?? ??? ??
??? ???
??? ??? ?
??? Data?
?? ?? ???
??(????)
If (loc = ?? and comp = ???ICT)
person = ???
elif (loc = ?? and comp = SK Planet)
person = ???
else
person = ???