iLMS知識社群ePortfolioeeClass學習平台空大首頁登入
位置: 吳俊逸 > AI
by 吳俊逸 2023-08-25 23:39:27, 回應(0), 人氣(299)
Basic AI Terminology | Assessment
(全文...)
by 吳俊逸 2022-11-16 00:33:35, 回應(0), 人氣(696)
Including Diffusion models​, Advanced language models​, Machine Programming​, Graph NN (GNNs)​, Self-supervision​, Advancements in Reinforcement Learning (RL)​, Multimodalities (Modeling with text, image and audio data)​ and Compression/ Tiny ML​ Topic​
(全文...)
by 吳俊逸 2022-06-08 12:28:01, 回應(0), 人氣(2756)
https://college.itri.org.tw/Home/LessonData?PosterGUID=9C4E6BC7-772F-441E-B68F-2CE6FAB181F5&fbclid=IwAR3ALbIST8Plf_EXzxJQva-_oZ7iKttK-F9MFcEdibpRntUTEXs7o7HLU7cOrange 資料探勘(Orange Data Mining,舊稱Orange 3) 是一個支援視覺化、圖示化介面的資料探索工具。使用Orange就可以像積木一樣,透過堆疊功能模組進行資料探勘( Data Mining)、機器學習 (Machine Learning)、圖像分析 (Image Analysis)、文字探勘 (Text Mining),方便使用者可以專注於探索性數據而不是編碼工作。因此Orange這種視覺化程式設計工具(Visual Programming Tools)可提供開發人員和資料科學家各式各樣的模組,讓資料處理、模型建置、訓練及部署機器學習模型更加快速且視覺化更容易上手!項目
(全文...)
by 吳俊逸 2022-01-27 12:26:29, 回應(0), 人氣(1871)
Ref: CUPOY AI時代的各種專業職務所需技能學習地圖整理Ref: 機器之心 https://i.am.ai/roadmap/這是一家德國軟體公司 AMAI GmbH 近期釋出的 GitHub 專案—AI 專家路線圖(AI-Expert-Roadmap)。該路線圖幾乎涵蓋了 AI 領域所有的知識點,並且每個知識點都有詳細的文件。有了這個路線圖的指導,或許能幫助你快速入門乃至成為 AI 領域的佼佼者。
(全文...)
by 吳俊逸 2022-01-04 09:12:14, 回應(0), 人氣(872)
REF: https://www.analyticsinsight.net/top-10-automl-libraries-for-implementing-in-your-machine-learning-projects/Auto-SklearnAuto-Sklearn is one of the top open-source AutoML libraries for machine learning projects. It is known as an automated machine learning toolkit and popular for providing freedom to users from algorithm section and hyperparameter tuning. This AutoML for ML projects leverages Bayesian optimization and meta-learning with Auto-sklearn 2.0.
(全文...)
by 吳俊逸 2022-01-04 09:08:25, 回應(0), 人氣(1020)
REF:https://ithelp.ithome.com.tw/articles/10276333Auto-sklearn 採用元學習 (Meta Learning) 選擇模型和超參數優化的方法作為搜尋最佳模型的重點。此 AutoML 套件主要是搜尋所有 Sklearn 機器學習演算法以模型的超參數,並使用貝葉斯優化 (Bayesian Optimization) 與自動整合 (Ensemble Selection) 的架構在有限時間內搜尋最佳的模型。第一版的 Auto-sklearn 於 2015 年發表在 NIPS(Neural Information Processing Systems) 會議上,論文名稱為 Efficient and Robust Automated Machine Learning。有別於其他的 AutoML 方法,Auto-sklearn 提出了元學習架構改善了貝葉斯優化在初始冷啟動的缺點,並提供一個好的採樣方向更快速尋找最佳的模型[1]。第二個版本於 2020 年發布,論文名稱為 Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning。在新的版本中修改了元學習架構,並不依賴元特徵來選擇模型選擇與調參策略。而是引入了一個元學習策略選擇器,根據資料集中的樣本數量和特徵,訂定了一個模型選擇的策略[3]。
(全文...)
by 吳俊逸 2021-09-11 11:59:38, 回應(0), 人氣(1518)
https://developer.nvidia.com/blog/new-on-ngc-catalog-samsung-sdss-brightrics-an-ai-accelerator-for-automating-and-accelerating-deep-learning-training/Samsung SDS Brightics, an AI Accelerator for Automating and Accelerating Deep Learning TrainingTraining AI models is an extremely time-consuming process. Without proper insight into a feasible alternative to time-consuming development and migration of model training to exploit the power of large, distributed clusters, training projects remain considerably long lasting. To address these issues, Samsung SDS developed the Brightics AI Accelerator. The Kubernetes-based, containerized application, is now available on the NVIDIA NGC catalog – a GPU-optimized hub for AI and HPC containers, pre-trained models, industry SDKs, and Helm charts that helps simplify and accelerate AI development and deployment processes.  
(全文...)
by 吳俊逸 2021-03-10 23:15:27, 回應(0), 人氣(2991)
key: 1) model export as (pkcls) 2) data export as (tab) 3) import Orange (install Orange3) & pickletrain your model, and save the model as pkcls. Moreover, save your test data as ta
(全文...)
by 吳俊逸 2020-06-08 00:00:35, 回應(0), 人氣(2178)
REF: https://machinelearningmastery.com/how-to-get-started-with-deep-learning-for-time-series-forecasting-7-day-mini-course/Deep learning methods offer a lot of promise for time series forecasting, such as the automatic learning of temporal dependence and the automatic handling of temporal structures like trends and seasonality.
(全文...)
by 吳俊逸 2020-05-10 22:28:24, 回應(0), 人氣(1085)
以下,將展示如何使用Orange3來顯示一組與所選參考圖像最相似的圖像。 Orange3將使用以下工作流程:
(全文...)
Prev12345Next