by 李彼德, 蔡萊恩
分享科學技術各種知識，歡迎喜愛科學技術的朋友們一同來聆聽。 目前主要的內容是來自於部落格的文章。 我們的部落格分別有 李彼德之家: https://peterlihouse.com/ fyanblog: https://fryanblog.com/ 歡迎大家想更近一步了解這些技術內容，可到我們的部落格觀看。 -- Hosting provided by <a href="https://www.soundon.fm/" target="_blank">SoundOn</a>
Language
🇨🇳
Publishing Since
7/22/2022
Email Addresses
1 available
Phone Numbers
0 available
April 23, 2024
從上述例子可以了解到針對很多語言上的應用，其實是需要網路有記憶功能，才有機會可以從前後字詞關係，去理解整個句子的意思，也就是語意理解的功能。因此，遞迴類神經網路(RNN)就是要去解決這樣的痛點而誕生的方法。 本篇文章為https://peterlihouse.com/%e9%a6%96%e9%a0%81/%e7%9f%a5%e8%ad%98%e5%88%86%e4%ba%ab/%e4%ba%ba%e5%b7%a5%e6%99%ba%e6%85%a7/%e9%81%9e%e8%bf%b4%e9%a1%9e%e7%a5%9e%e7%b6%93%e7%b6%b2%e8%b7%afrecurrent-neural-networkrnn%e4%bb%8b%e7%b4%b9/ -- Hosting provided by <a href="https://www.soundon.fm/">SoundOn</a>
August 7, 2023
為何要使用自編碼器? 自編碼器是一種自監督式學習(self-supervised learning)的方法，不需要像監督式學習(supervised learning)定義每筆資料的標籤(label)，因此，在訓練上是相對方便的一個技術。而待自編碼器訓練完成後，可學習資料的潛在表示法(latent representation)，可應用在異常檢測(anomaly detection)，圖像生成(image generation)等等領域。 <a href="https://peterlihouse.com/%e9%a6%96%e9%a0%81/%e7%9f%a5%e8%ad%98%e5%88%86%e4%ba%ab/%e8%87%aa%e7%b7%a8%e7%a2%bc%e5%99%a8%e4%bb%8b%e7%b4%b9autoencoder/">本篇文章連結</a> 個人部落格： <a href="https://peterlihouse.com/">李彼德之家</a> 粉絲專頁： <a href="https://www.facebook.com/profile.php?id=100091646083056">李彼德之家</a> -- Hosting provided by <a href="https://www.soundon.fm/">SoundOn</a>
May 22, 2023
那我們該如何尋找網路的權重呢?其實存在很多種方法，以最簡單而言，可以隨機給定一組權重，來看看結果好不好?如果不好，就一直反覆隨機嘗試不同權重。而這樣的方法，如果是非常非常簡單的模型，權重在非常少的數目下，確實有可能可以找到不錯的權重。可是如果網路越來越複雜，所需要決定的權重很多，我們就很難透過這種方法去尋找，因為最後就會發現排列組合太多了，根本難以找到最佳的權重。而反向傳播法正是為了要解決這樣的問題，透過從理論建立一套系統化的方法，讓我們可以很方便快速地尋找到最佳權重。 <a href="https://peterlihouse.com/%e9%a6%96%e9%a0%81/%e7%9f%a5%e8%ad%98%e5%88%86%e4%ba%ab/%e9%a1%9e%e7%a5%9e%e7%b6%93%e7%b6%b2%e8%b7%af-%e5%8f%8d%e5%90%91%e5%82%b3%e6%92%ad%e6%b3%95%e4%b8%80-%e7%99%bd%e8%a9%b1%e6%96%87%e5%b8%b6%e6%82%a8%e4%ba%86%e8%a7%a3%e5%8f%8d%e5%90%91%e5%82%b3/"> 本篇文章連結</a> -- Hosting provided by <a href="https://www.soundon.fm/">SoundOn</a>
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at [email protected] for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.