Theoretical results suggest that in order to learn the kind of complicated
functions that can represent high-level abstractions (e.g., in
vision, language, and other AI-level tasks), one may need deep architectures.
Deep architectures are composed of multiple levels of non-linear
operations, such as in neural nets with many hidden layers or in complicated
propositional formulae re-using many sub-formulae. Searching
the parameter space of deep architectures is a difficult task, but learning
algorithms such as those for Deep Belief Networks have recently been
proposed to tackle this problem with notable success, beating the stateof-
the-art in certain areas. This monograph discusses the motivations
and principles regarding learning algorithms for deep architectures, in
particular those exploiting as building blocks unsupervised learning of
single-layer models such as Restricted Boltzmann Machines, used to
construct deeper models such as Deep Belief Networks.
具體描述
讀後感
講的比較清晰，提供瞭關鍵的數學計算內容，作為綜述來看是很不錯的選擇。但是不親自推一遍細節很難透徹理解，需要一些機器學習、隨機過程、信息論和最優化理論的知識。理論框架介紹的很清楚，有助於理解目前各類變種。
評分具體內容： More precisely ,functions that can be compactly represented by a depth k architecture might require an exponential number of computational elements to be represented by a depth k-1 architecture. 這句意思是k-1層架構可以錶示的函數需要的計算元素...
評分具體內容： More precisely ,functions that can be compactly represented by a depth k architecture might require an exponential number of computational elements to be represented by a depth k-1 architecture. 這句意思是k-1層架構可以錶示的函數需要的計算元素...
評分講的比較清晰，提供瞭關鍵的數學計算內容，作為綜述來看是很不錯的選擇。但是不親自推一遍細節很難透徹理解，需要一些機器學習、隨機過程、信息論和最優化理論的知識。理論框架介紹的很清楚，有助於理解目前各類變種。
評分具體內容： More precisely ,functions that can be compactly represented by a depth k architecture might require an exponential number of computational elements to be represented by a depth k-1 architecture. 這句意思是k-1層架構可以錶示的函數需要的計算元素...
用戶評價
Deep Belief Networks / Restricted Boltzmann Machine
评分非常insightful的小書，把deep learning背後的philosophy以及現有的一些results闡述得很清楚。DL現在應用很廣，炒得很火，體係韆瘡百孔，這是好事。Bengio通過此書指瞭些明路。另此書不適閤DL入門。
评分RBM開始實在跟不上瞭，棄…前麵的intuition挺有意思的…
评分Deep Belief Networks / Restricted Boltzmann Machine
评分RBM開始實在跟不上瞭，棄…前麵的intuition挺有意思的…
相關圖書
本站所有內容均為互聯網搜索引擎提供的公開搜索信息，本站不存儲任何數據與內容，任何內容與數據均與本站無關，如有需要請聯繫相關搜索引擎包括但不限於百度，google,bing,sogou 等
© 2025 onlinetoolsland.com All Rights Reserved. 本本书屋 版权所有