<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Machine Learning - 標籤 - DataSci Ocean</title><link>https://datasciocean.com/tags/machine-learning/</link><description>Machine Learning - 標籤 - DataSci Ocean</description><generator>Hugo -- gohugo.io</generator><language>zh-TW</language><managingEditor>l066858998@gmail.com (Hong-Wei Wu)</managingEditor><webMaster>l066858998@gmail.com (Hong-Wei Wu)</webMaster><copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright><lastBuildDate>Sat, 11 Feb 2023 00:00:00 +0000</lastBuildDate><atom:link href="https://datasciocean.com/tags/machine-learning/" rel="self" type="application/rss+xml"/><item><title>AWS ML Service 介紹：用 Amazon SageMaker 打造機器學習開發流程</title><link>https://datasciocean.com/other/aws-ml-service/</link><pubDate>Sat, 11 Feb 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/other/aws-ml-service/</guid><description>&lt;div class="featured-image">
                &lt;img src="/other/aws-ml-service/featured-image.jpeg" referrerpolicy="no-referrer">
            &lt;/div>AWS 機器學習相關服務可分為兩層：直接呼叫 API 的 AI Services，以及讓開發者自建模型的 ML Services。本文以 Amazon SageMaker Studio、Distributed Training 與 Clarify 三項工具，介紹如何簡化機器學習的開發、訓練與偏誤分析流程。</description></item><item><title>AWS AI Services 完整介紹：13 大應用領域與代表服務一次看懂</title><link>https://datasciocean.com/other/aws-ai-service/</link><pubDate>Fri, 10 Feb 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/other/aws-ai-service/</guid><description>&lt;div class="featured-image">
                &lt;img src="/other/aws-ai-service/featured-image.jpeg" referrerpolicy="no-referrer">
            &lt;/div>AWS 在機器學習領域的產品線相當龐雜，本文聚焦最上層的 AI Services，介紹健康照護、工業、異常偵測等 13 個應用領域的代表性服務，讓開發者不需自己訓練模型，也能把 AI 能力直接接進應用程式。</description></item><item><title>使用機器學習解決問題的五步驟：模型推論</title><link>https://datasciocean.com/ai-concept/model-inference/</link><pubDate>Sun, 05 Feb 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/ai-concept/model-inference/</guid><description>&lt;div class="featured-image">
                &lt;img src="/ai-concept/model-inference/featured-image.jpg" referrerpolicy="no-referrer">
            &lt;/div>機器學習解決問題五步驟的最後一篇：模型推論。介紹模型推論與模型訓練的差異，以及 Pruning 與 Quantization 兩種模型最佳化方法。</description></item><item><title>使用機器學習解決問題的五步驟：模型評估</title><link>https://datasciocean.com/ai-concept/model-evaluate/</link><pubDate>Thu, 02 Feb 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/ai-concept/model-evaluate/</guid><description>&lt;div class="featured-image">
                &lt;img src="/ai-concept/model-evaluate/featured-image.jpg" referrerpolicy="no-referrer">
            &lt;/div>模型訓練完之後，要怎麼知道它好不好用？本文介紹模型評估的概念、Overfitting 是什麼，以及分類與回歸任務常用的評估指標</description></item><item><title>使用機器學習解決問題的五步驟：模型訓練</title><link>https://datasciocean.com/ai-concept/model-training/</link><pubDate>Sun, 29 Jan 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/ai-concept/model-training/</guid><description>&lt;div class="featured-image">
                &lt;img src="/ai-concept/model-training/featured-image.jpg" referrerpolicy="no-referrer">
            &lt;/div>機器學習入門系列第三篇：帶你搞懂「模型訓練」到底在訓練什麼，拆解參數與損失函數的關係，並介紹超參數、常用函式庫與常見模型種類。</description></item><item><title>機器學習解決問題五步驟之二：建立資料集為何最花時間？</title><link>https://datasciocean.com/ai-concept/prepare-dataset/</link><pubDate>Sat, 28 Jan 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/ai-concept/prepare-dataset/</guid><description>&lt;div class="featured-image">
                &lt;img src="/ai-concept/prepare-dataset/featured-image.jpg" referrerpolicy="no-referrer">
            &lt;/div>「建立資料集」是機器學習五步驟中最重要也最花時間的一步，統計上佔了近 80% 的專案時間。本文帶你認識資料收集、資料檢查、統計摘要與資料視覺化四個階段。</description></item><item><title>使用機器學習解決問題的五步驟：定義問題</title><link>https://datasciocean.com/ai-concept/define-problem/</link><pubDate>Fri, 27 Jan 2023 00:00:00 +0000</pubDate><author><name>Hong-Wei Wu</name></author><guid>https://datasciocean.com/ai-concept/define-problem/</guid><description>&lt;div class="featured-image">
                &lt;img src="/ai-concept/define-problem/featured-image.jpg" referrerpolicy="no-referrer">
            &lt;/div>機器學習解決問題五步驟系列的第一篇：說明「定義問題」這一步到底在做什麼，並區分監督式學習（回歸、分類）與非監督式學習（分群）各自適合的任務類型。</description></item></channel></rss>