人工智慧 / DeepLearning
◎ 如果有一層隱藏層學不會的事,那就再加一層!
2016 年的春天,Google DeepMind 團隊的 AlphaGo 專案打敗了世界棋手,AI 世代的 Deep Learning 威力讓全世界 70 億人都驚呆了!
屬於機器學習一種的深度學習,透過層層類神經網路,儼然成為了最簡單卻又最深奧的技術,最早用於電腦視覺(Computer Vision)。現今主流還有應用於自然語言處理的RNN,可處理時間序列、判斷語意,以及近期最夯的生成式對抗網路(GAN)、及新興起的強化學習(Reinforcement Learning)。
◎ 那麼,如果有 N 層隱藏層學不會的事,那 N+1 層就會了嗎...
雖說深度學習強在他的「深」,但目前的研究結果也顯示了並非有越多層、成效就越好,從CNN中的梯度下降法(Gradient Descent Method)來看,當迭代過多層神經網路,容易導致Vanishing Gradient,在哪邊都看不出最小值。目前看來,要降低錯誤率還是需要較複雜的網路架構。
...說了這麼多,要進行深度學習,電腦需要的只是足夠量的資料,而你,需要的只是幾本好書。
相關書籍
-
60折
$960Natural Language Processing with TensorFlow
-
50折
$1,150Machine Learning with Python Cookbook: Practical Solutions from Preprocessing to Deep Learning
-
80折
$1,960TensorFlow for Deep Learning: From Linear Regression to Reinforcement Learning
-
60折
$918Machine Learning with TensorFlow
-
80折
$1,088Deep Learning with TensorFlow - Second Edition: Explore neural networks with Python
-
80折
$1,088Tensorflow Deep Learning Projects
-
80折
$960R Deep Learning Projects: Master the techniques to train and deploy neural networks in R
-
90折
$3,780Hybrid Intelligence for Image Analysis and Understanding
-
60折
$1,248Deep Learning: A Practitioner's Approach (Paperback)
-
90折
$1,575Deep Learning for Computer Architects (Synthesis Lectures on Computer Architecture)
-
25折
$299Hands-On Deep Learning with TensorFlow
-
60折
$876Deep Learning with Theano
-
50折
$749Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms (Paperback)
-
90折
$1,764MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence (Paperback)
-
80折
$2,144Deep Learning: Practical Neural Networks with Java
-
50折
$990Hands-On Machine Learning with Scikit-Learn and TensorFlow (Paperback)
-
60折
$2,538Deep Learning for Medical Image Analysis
-
90折
$2,070Deep Learning with GPUs: For the beginner
-
23折
$399Building Machine Learning Projects with TensorFlow (Paperback)
-
25折
$399Java Deep Learning Essentials (Paperback)
-
80折
$3,520Selective Visual Attention: Computational Models and Applications (Hardcover)
-
90折
$4,329Reinforcement Learning and Approximate Dynamic Programming for Feedback Control (Hardcover)