Machine Learning week 3 quiz : Logistic Regression

原创 2015年11月17日 19:03:20

Logistic Regression

5 试题

1. 

Suppose that you have trained a logistic regression classifier, and it outputs on a new example x a prediction hθ(x) = 0.4. This means (check all that apply):

Our estimate for P(y=0|x;θ) is 0.4.

Our estimate for P(y=0|x;θ) is 0.6.

Our estimate for P(y=1|x;θ) is 0.4.

Our estimate for P(y=1|x;θ) is 0.6.

2. 

Suppose you have the following training set, and fit a logistic regression classifier hθ(x)=g(θ0+θ1x1+θ2x2).

Which of the following are true? Check all that apply.

Adding polynomial features (e.g., instead using hθ(x)=g(θ0+θ1x1+θ2x2+θ3x21+θ4x1x2+θ5x22) ) could increase how well we can fit the training data.

At the optimal value of θ (e.g., found by fminunc), we will have J(θ)0.

Adding polynomial features (e.g., instead using hθ(x)=g(θ0+θ1x1+θ2x2+θ3x21+θ4x1x2+θ5x22) ) would increase J(θ)because we are now summing over more terms.

If we train gradient descent for enough iterations, for some examples x(i) in the training set it is possible to obtain hθ(x(i))>1.

3. 

For logistic regression, the gradient is given by θjJ(θ)=mi=1(hθ(x(i))y(i))x(i)j. Which of these is a correct gradient descent update for logistic regression with a learning rate of α? Check all that apply.

θ:=θα1mmi=1(hθ(x(i))y(i))x(i).

θj:=θjα1mmi=1(θTxy(i))x(i)j (simultaneously update for all j).

θ:=θα1mmi=1(11+eθTx(i)y(i))x(i).

θ:=θα1mmi=1(θTxy(i))x(i).

4. 

Which of the following statements are true? Check all that apply.

Linear regression always works well for classification if you classify by using a threshold on the prediction made by linear regression.

For logistic regression, sometimes gradient descent will converge to a local minimum (and fail to find the global minimum). This is the reason we prefer more advanced optimization algorithms such as fminunc (conjugate gradient/BFGS/L-BFGS/etc).

The cost function J(θ) for logistic regression trained with m1 examples is always greater than or equal to zero.

The sigmoid function g(z)=11+ez is never greater than one (>1).

5. 

Suppose you train a logistic classifier hθ(x)=g(θ0+θ1x1+θ2x2). Suppose θ0=6,θ1=1,θ2=0. Which of the following figures represents the decision boundary found by your classifier?

Figure:

Figure:

Figure:

Figure:


版权声明:本文为博主原创文章,未经博主允许不得转载。 举报

相关文章推荐

Coursera Machine Learning 第三周 quiz Logistic Regression

1. Suppose that you have trained a logistic regression classifier, and it outputs on a new exam...

machine learning error correction

1, Suppose you have the following training set, and fit a logistic regression classifier hθ(x)=g(θ0+...

我是如何成为一名python大咖的?

人生苦短,都说必须python,那么我分享下我是如何从小白成为Python资深开发者的吧。2014年我大学刚毕业..

Machine Learning week 10 quiz: Large Scale Machine Learning

Large Scale Machine Learning 5 试题 1.  Suppose you are training a logistic regression ...

Coursera Machine Learning 第十周 quiz Large Scale Machine Learning

1 point 1.  Suppose you are training a logistic regression classifier using stochastic ...

Coursera Machine Learning 第六周 quiz Machine Learning System Design

有用就点个赞吧 1 point 1.  You are working on a spam classification system using regularized logis...

Machine Learning week 3 quiz : Logistic Regression

Logistic Regression 5 试题 1.  Suppose that you have trained a logist...

Machine Learning week 3 quiz: programming assignment-Logistic Regression

一、ex2.m: the main .m file to call other function files % matlab %% Machine Learning Online Class - ...

Coursera Machine Learning Week 3.1: Logistic Regression

这一周讲的是classification中最基本很简单的Logistic Regression 为什么要有Logistic Regression,分类问题其实Linear Regression也可以...

Machine Learning week 3 quiz : Regularization

Regularization 5 试题 1.  You are training a classification model wit...

Machine Learning week 2 quiz: programming assignment-Linear Regression

Instructions Download the programming assignment here. This ZIP file contains the instructions in a...
返回顶部
收藏助手
不良信息举报
您举报文章:深度学习:神经网络中的前向传播和反向传播算法推导
举报原因:
原因补充:

(最多只允许输入30个字)