[UIST 2022] BO as Assistant: Using Bayesian Optimization for Asynchronously G...Yuki Koyama
Bayesian optimization can be used to efficiently solve optimization problems defined by human preferences. The researchers propose using BO as an assistant that learns a designer's preferences from their manipulations of sliders without requiring explicit feedback. They extract relative preference data from the slider interactions to use preferential Bayesian optimization. This allows the designer freedom while still benefiting from the intelligent sampling of BO. They demonstrate this approach for photo color enhancement and procedural material design.
Personalized News Recommendation (Stream Data Based)Umesh Singla
1. The document discusses personalized news article recommendation using a contextual bandit approach to balance exploration and exploitation when suggesting articles to users.
2. It provides examples of contextual bandits in web services and clinical decision making.
3. The key challenge is how to quickly identify relevant news stories on a personal level for both new and existing users given changing article relevance over time.
4. Two linear contextual bandit algorithms, LinUCB with disjoint and hybrid models, are proposed to learn the best policy for selecting news articles to maximize click-through rates based on user and article features.
Semi supervised, weakly-supervised, unsupervised, and active learningYusuke Uchida
An overview of semi supervised learning, weakly-supervised learning, unsupervised learning, and active learning.
Focused on recent deep learning-based image recognition approaches.
Research Trends in Editing image using GAN (TAGAN, Editable GAN)DaeJin Kim
The document summarizes research on using generative adversarial networks (GANs) to edit images using text. It discusses Text-Adaptive GAN, which can manipulate images based on natural language descriptions, and Editable GAN, which can simultaneously generate and edit faces. It then proposes a model called Editable Text-Adaptive GAN that combines aspects of these two models to allow generating and editing images using natural language descriptions. Key aspects discussed include the model structure, use of a connection network and text-adaptive discriminator, and potential limitations and areas for improvement.
[論文読み]Effective Approaches to Attention-based Neural Machine Translationhirono kawashima
This document discusses two approaches to attention in neural machine translation (NMT): global attention and local attention. It presents the results of experiments comparing these two approaches on English-German translation tasks. Global attention considers the entire input sequence at each time step, while local attention only considers a subset. The experiments show that both approaches improve over non-attention-based NMT, but local attention performs slightly better, achieving a BLEU score of 24.61 on the WMT 2014 test set and 25.9 on the WMT 2015 test set.
These are the slides of my invited talk at the REVEAL workshop at RecSys 2019. The workshop focuses on the offline evaluation for recommender systems, and this year’s focus was on Reinforcement Learning. Although not directly related to reinforcement learning, it is clear that there are connections to what research in reinforcement learning is attempting to achieve (defining the rewards) and metrics that are optimized by recommender systems. I presented various works and personal thoughts on how to develop metrics of user engagement, which recommender systems can optimize for. An important message was that, for recommender systems to work both in the short and the long-term, it is important to consider the heterogeneity of both user and content to formalise the notion of engagement, and in turn design the appropriate metrics to capture these and optimize for. One way to achieve this is to follow these four steps: 1) Understanding intents; 2) Optimizing for the right metric; 3) Acting on segmentation; and 4) Thinking about diversity.
An previous version of this talk was given to UMAP 2019. See https://www.slideshare.net/mounialalmas/metrics-engagement-personalization
This is a brief review of net lift models based on the presentation I did at Truecar in June, 2013 after I attended the training provided by SAS Institute. Recently, I added a few things to the slides after I reviewed several online examples and papers.
This document describes 3D convolutional neural networks (CNNs) for action recognition in videos. It discusses the C3D model, which applies 3D convolutional filters to video data. C3D can be pretrained on the Sports-1M dataset and then used to extract features from video frames. The document provides instructions for compiling C3D, extracting features from videos, and reading the output features in MATLAB or Python for use in action recognition tasks.
- The document describes a reinforcement learning method using deep neural networks called DQN that was able to learn successful policies to play 49 Atari 2600 games directly from raw pixel inputs, outperforming prior methods on 43 games.
- DQN trained large neural networks using a reinforcement learning signal and stochastic gradient descent in a stable manner. Its performance was comparable to human-level performance on over half the games.
- The method took high-dimensional video game inputs and used a convolutional neural network architecture to learn policies without additional domain knowledge beyond the inputs, actions, and rewards.
第六回全日本コンピュータビジョン勉強会資料 UniT (旧題: Transformer is all you need)Yasunori Ozaki
第六回全日本コンピュータビジョン勉強会資料です。今回は、 UniT: Multimodal Multitask Learning with a Unified Transformer を紹介します。提案手法であるUniTは自然言語、ビジョン、 Vision and Language のタスクをそれぞれ統一的に解けるTransformer になります。
Fast, deterministic, and verifiable computations with WebAssembly. WASM on th...Fluence Labs
Video: https://youtu.be/Cj6nOyBnQiY
Fast, Deterministic, and Verifiable Computations for Blockchains with WebAssembly
Speaker: Mike Voronov, @VMS11
Deterministic computations are essential for building open blockchain networks where any state transition needs to be verified by multiple network nodes. In the Fluence network computations generally happen off-chain but can be partially repeated on-chain in the case if a dispute over computation results is raised.
We will discuss how to achieve computational determinism for arbitrary WebAssembly programs; how to implement an on-chain dispute resolution by running a WebAssembly interpreter in an Ethereum smart contract; how to employ existing JIT technologies to achieve fast WebAssembly execution. Finally, how to efficiently merkelize virtual machine state, count spent gas, and resolve verification game disputes.
These are the slides of my invited talk at the REVEAL workshop at RecSys 2019. The workshop focuses on the offline evaluation for recommender systems, and this year’s focus was on Reinforcement Learning. Although not directly related to reinforcement learning, it is clear that there are connections to what research in reinforcement learning is attempting to achieve (defining the rewards) and metrics that are optimized by recommender systems. I presented various works and personal thoughts on how to develop metrics of user engagement, which recommender systems can optimize for. An important message was that, for recommender systems to work both in the short and the long-term, it is important to consider the heterogeneity of both user and content to formalise the notion of engagement, and in turn design the appropriate metrics to capture these and optimize for. One way to achieve this is to follow these four steps: 1) Understanding intents; 2) Optimizing for the right metric; 3) Acting on segmentation; and 4) Thinking about diversity.
An previous version of this talk was given to UMAP 2019. See https://www.slideshare.net/mounialalmas/metrics-engagement-personalization
This is a brief review of net lift models based on the presentation I did at Truecar in June, 2013 after I attended the training provided by SAS Institute. Recently, I added a few things to the slides after I reviewed several online examples and papers.
This document describes 3D convolutional neural networks (CNNs) for action recognition in videos. It discusses the C3D model, which applies 3D convolutional filters to video data. C3D can be pretrained on the Sports-1M dataset and then used to extract features from video frames. The document provides instructions for compiling C3D, extracting features from videos, and reading the output features in MATLAB or Python for use in action recognition tasks.
- The document describes a reinforcement learning method using deep neural networks called DQN that was able to learn successful policies to play 49 Atari 2600 games directly from raw pixel inputs, outperforming prior methods on 43 games.
- DQN trained large neural networks using a reinforcement learning signal and stochastic gradient descent in a stable manner. Its performance was comparable to human-level performance on over half the games.
- The method took high-dimensional video game inputs and used a convolutional neural network architecture to learn policies without additional domain knowledge beyond the inputs, actions, and rewards.
第六回全日本コンピュータビジョン勉強会資料 UniT (旧題: Transformer is all you need)Yasunori Ozaki
第六回全日本コンピュータビジョン勉強会資料です。今回は、 UniT: Multimodal Multitask Learning with a Unified Transformer を紹介します。提案手法であるUniTは自然言語、ビジョン、 Vision and Language のタスクをそれぞれ統一的に解けるTransformer になります。
Fast, deterministic, and verifiable computations with WebAssembly. WASM on th...Fluence Labs
Video: https://youtu.be/Cj6nOyBnQiY
Fast, Deterministic, and Verifiable Computations for Blockchains with WebAssembly
Speaker: Mike Voronov, @VMS11
Deterministic computations are essential for building open blockchain networks where any state transition needs to be verified by multiple network nodes. In the Fluence network computations generally happen off-chain but can be partially repeated on-chain in the case if a dispute over computation results is raised.
We will discuss how to achieve computational determinism for arbitrary WebAssembly programs; how to implement an on-chain dispute resolution by running a WebAssembly interpreter in an Ethereum smart contract; how to employ existing JIT technologies to achieve fast WebAssembly execution. Finally, how to efficiently merkelize virtual machine state, count spent gas, and resolve verification game disputes.
Introduce twMVC
list text here ASP.NET MVC 可以吃嗎?
ASP.NET MVC 的成功案例
什麼是 MVC
MVC 概觀
ASP.NET MVC 對物件導向的潛移默化
View 簡介
View Engine
HTML Helper
Partial View
Razer Helper 小技巧
JavaScript is a client-side script language, but we can use it on server side programming now. However, it is still difficult to write server-side application for front-end developer.
Here we try to find a solution to write server-side script that developer only need to understand and have client-side experience.
ASP.NET Core MVC 2.2從開發到測試 - Development & Unit Testing江華 奚
說明從ASP.NET MVC 5遷移至ASP.NET Core 2.x會遭遇哪技術上的變更,要如何將既有專案項目移轉到新的ASP.NET Core環境,並做出哪些調整。同時運用ASP.NET Core內建的Dependency Injection相依性注入來註冊你的服務,以達成IoC控制反轉的目的。最後用ASP.NET Core內建的單元測試,包括MStest, NUnit, xUnit來測試專案Function,達到提升品質的目的。在測試的同時,一併介紹如何使用Test Explorer, Live Testing, Code Coverage工具來輔助測試。
碼魔法網站:https://www.codemagic.com.tw/
碼魔法FB : https://www.facebook.com/CodeMagicTw/
ASP.NET Core MVC 2.2 - Development & Unit Testing. How to Choose between NET Core and .NET Framework. Choose between ASP.NET Core 2.1 and ASP.NET Core 2.2.
ASP.NET MVC 的 Model 並不等同於 Entity Framework,這一次將說明如何使用 ADO.NET 來做為 MVC 的 Model,並且介紹 Enterprise Library Data Access Application Block以及實作分層讓 Model 讓 Web Forms 專案可以共用。
ASP.NET MVC 的 Model 並不等同於 Entity Framework,這一次將說明如何使用 ADO.NET 來做為 MVC 的 Model,並且介紹 Enterprise Library Data Access Application Block以及實作分層讓 Model 讓 Web Forms 專案可以共用。
TDD 貌似不難,但在實務上能推行與貫徹的團隊卻是少之又少,甚至被視為是一種不切實際的開發方式。在這次分享中,將搭配 demo 來介紹幾個貫徹 TDD 所需要的重要概念,
包含:
IoC
Unit testing
Web UI testing
BDD
期望讓大家在未來的工作上,也可以透過 TDD 快樂地開發。
by twMVC http://mvc.tw
16. JSONController ( MVC Web API )
Controller ( MVC ) View ( MVC )
View
HTML & CSS
ViewModel
JS
Model
( JSON )
RESTful ( Get )
RESTful (Post)
BindingUse
RESTful (Delete)
RESTful (Put)
渲染
Post Action
Put Action
Delete Action
Get Action
J
S
M
V
V
M
資料來源
Sky Demo
25. 資料來源
JSONController ( MVC Web API )
Controller ( MVC )
View ( MVC )
View - HTML & CSS
ViewModel - JS
Model – JS ( JSON )
RESTful ( Get )
RESTful (Post)
BindingUse
RESTful (Delete)
RESTful (Put)
渲染
Post Action
Put Action
Delete Action
Get Action
J
S
M
V
V
M資料來源
Sky Demo
40. 40
ASP.NET SPA Ember Durandal
Breeze/
Kunckout
Breeze/
Angular
Hot Towel
ToDo sample ★ ★ ★ ★
Bare template ★ ★
Uses Angular ★
Uses Breeze ★ ★ ★
Uses Durandal ★ ★
Uses Ember ★
Uses Knockout ★ ★ ★ ★
Navigation and history
★ ★ ★ ★
41. 41
ASP.NET SPA Ember Durandal
Breeze/
Kunckout
Breeze/
Angular
Hot Towel
ToDo sample ★ ★ ★ ★
Bare template ★ ★
Uses Angular ★
Uses Breeze ★ ★ ★
Uses Durandal ★ ★
Uses Ember ★
Uses Knockout ★ ★ ★ ★
Navigation and history
★ ★ ★ ★
43. 資料來源
JSONController ( MVC Web API )
Controller ( MVC )
View ( MVC )
View - HTML & CSS
ViewModel - JS
Model – JS ( JSON )
RESTful ( Get )
RESTful (Post)
BindingUse
RESTful (Delete)
RESTful (Put)
渲染
Post Action
Put Action
Delete Action
Get Action
J
S
M
V
V
M資料來源
Sky Demo