深度學習框架簡史

{"type":"doc","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"過去⼗年，機器學習（尤其是深度學習領域）湧現了⼤量算法和應⽤。在這些深度學習算法和應⽤湧現的背後，是各種各樣的深度學習⼯具和框架。它們是機器學習⾰命的腳⼿架：TensorFlow和PyTorch等深度學習框架的⼴泛使⽤，使許多機器學習從業者能夠使⽤適合領域的特定編程語⾔和豐富的構建模塊更容易地組裝模型。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"回顧深度學習框架的演變，我們可以清楚地看到深度學習框架和深度學習算法之間的緊密耦合關係。這種相互依賴的良性循環推動了深度學習框架和工具的快速發展。"}]},{"type":"image","attrs":{"src":"https:\/\/uploader.shimo.im\/f\/3CflgwRjg74mVYLB.png!thumbnail","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"heading","attrs":{"align":null,"level":4},"content":[{"type":"text","text":"石器時代（21 世紀初）"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"神經網絡的概念已經出現一段時間了。在 21 世紀初之前，有一些工具可以用來描述和開發神經網絡。這些工具包括 MATLAB、OpenNN、Torch 等，它們要麼不是專門爲神經網絡模型開發定製的，要麼擁有複雜的用戶 api，缺乏 GPU 支持。在此期間，ML 實踐者在使用這些原始的深度學習框架時不得不做很多繁重的工作。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/uploader.shimo.im\/f\/7yJfokK3AfUKWOEL.png!thumbnail","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"heading","attrs":{"align":null,"level":4},"content":[{"type":"text","text":"青銅時代（~2012 年）"}]}]}