香港科技大学TensorFlow三天速成课件1.pptxVIP

TensorFlow @UST;;TensorFlow @UST;Shocking IT NEWS last years?;/parallelforall/page/5/;/parallelforall/page/5/;http://respondr.io/7-ways-machine-learning-is-already-affecting-your-world/;Machine Learning is Already Affecting Your World;如果要建造一艘船，不要一起鼓勵人們收集木材， 不要分配任務和工作， 而應該教他們漫長的海洋無限遠。;Google Neural Machine Translation (Sep 2016);/store/apps/details?id=com.baidu.research.talktypehl=en;/store/apps/details?id=com.fitnow.loseithl=en;Smart Reply: Promising results Seen 78%, Used 31.9%;/ ;/blog/deep-learning-ai-startups-market-map-company-list/;Rule based programming VS data driven learning;How can we develop?;Smart Reply: Promising results Seen 78%, Used 31.9%;Rule based programming VS data driven learning;;/fchollet/status/830499993450450944/;/fchollet/status/830499993450450944/;TensorFlow;What is a Data Flow Graph?;Installing TensorFlow;Check installation and version;TensorFlow Hello World!;Computational Graph;TensorFlow Mechanics ;Computational Graph;Placeholder ;TensorFlow Mechanics ;Everything is Tensor;Tensor Ranks, Shapes, and Types;Tensor Ranks, Shapes, and Types;Tensor Ranks, Shapes, and Types;TensorFlow Mechanics ;Machine Learning Basics;Regression;Predicting exam score: regression;Regression (data);Regression (presentation);(Linear) Hypothesis;(Linear) Hypothesis;Which hypothesis is better?;Which hypothesis is better?;Cost function;Cost function;Cost function;Simplified hypothesis in TF;Goal: Minimize cost;What cost(W) looks like?;What cost(W) looks like?;What cost(W) looks like?;How to minimize cost?;Formal definition;Gradient descent algorithm in TF;TensorFlow Mechanics ;Build graph using TF operations;Build graph using TF operations;Run/update graph and get results;import tensorflow as tf # X and Y data x_train = [1, 2, 3] y_train = [1, 2, 3] W = tf.Variable(tf.random_normal([1]), name=weight) b = tf.Variable(tf.random_normal([1]), name=bias) # Our hypothesis XW+b hypothesis = x_train * W + b # cost/loss function cost = tf.reduce_mean(tf.square(hypothesis