Gain insights into machine learning algorithms like regression, deep learning, and SVMs. Learn about Python, probability theory, and optimization through practical coding exercises. Delve into ML intricacies.

fundamentals_of_machine_learning.tar.gz

chapter 2 job 1

chapter 2 job 2

draw graphs

Run SPA

Run SPA Plot

Run SPA-copy

draw-graphs-code-widget

export term

code_widget

The machine learning field is rapidly advancing today due to the availability of large datasets and the ability to process big data efficiently. Moreover, several new techniques have produced groundbreaking results for standard machine learning problems.

This course provides a detailed description of different machine learning algorithms and techniques, including regression, deep learning, reinforcement learning, Bayes nets, support vector machines (SVMs), and decision trees. The course also offers sufficient mathematical details for a deeper understanding of how different techniques work. An overview of the Python programming language and the fundamental theoretical aspects of ML, including probability theory and optimization, is also included. The course contains several practical coding exercises as well.

By the end of the course, you will have a deep understanding of different machine-learning methods and the ability to choose the right method for different applications.

Mastering Machine Learning Theory and Practice

**(Fill in the blank)** The rising loss value is a hint that the learning rate is ______.

(Fill in the blank) The rising loss value is a hint that the learning rate is ______.

**(Fill in the blank)** In genetic algorithms, parent individuals are allowed to reproduce by taking any two individuals and swapping parts of their genes at a certain transition point. This operation is called _______.

(Fill in the blank) In genetic algorithms, parent individuals are allowed to reproduce by taking any two individuals and swapping parts of their genes at a certain transition point. This operation is called _______.

**(Fill in the blank)** If the training examples appear randomly, then the training examples provide a random walk around the true gradient descent. These algorithms are hence called ______.

(Fill in the blank) If the training examples appear randomly, then the training examples provide a random walk around the true gradient descent. These algorithms are hence called ______.

**(True or False)** True local minima are increasingly difficult to realize in higher dimensions.

(True or False) True local minima are increasingly difficult to realize in higher dimensions.

**(Fill in the blank)** To be a true local minimum, it is necessary that all changes and all combinations of changes of all directions of the parameters lead to ______ loss values.

(Fill in the blank) To be a true local minimum, it is necessary that all changes and all combinations of changes of all directions of the parameters lead to ______ loss values.

$$
\mathbf{w} \leftarrow \mathbf{w}-\alpha \frac{\mathbf{m} /\left(1-\alpha_{1}\right)}{\sqrt{\mathbf{v} /\left(1-\alpha_{2}\right)}+\epsilon},
$$

**(Fill in the blank)** The small factor $\epsilon$ is added to prevent possible ___________.


<math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi mathvariant="bold">w</mi><mo>←</mo><mi mathvariant="bold">w</mi><mo>−</mo><mi>α</mi><mfrac><mrow><mi mathvariant="bold">m</mi><mi mathvariant="normal">/</mi><mrow><mo fence="true">(</mo><mn>1</mn><mo>−</mo><msub><mi>α</mi><mn>1</mn></msub><mo fence="true">)</mo></mrow></mrow><mrow><msqrt><mrow><mi mathvariant="bold">v</mi><mi mathvariant="normal">/</mi><mrow><mo fence="true">(</mo><mn>1</mn><mo>−</mo><msub><mi>α</mi><mn>2</mn></msub><mo fence="true">)</mo></mrow></mrow></msqrt><mo>+</mo><mi>ϵ</mi></mrow></mfrac><mo separator="true">,</mo></mrow><annotation encoding="application/x-tex">\mathbf{w} \leftarrow \mathbf{w}-\alpha \frac{\mathbf{m} /\left(1-\alpha_{1}\right)}{\sqrt{\mathbf{v} /\left(1-\alpha_{2}\right)}+\epsilon},
</annotation></semantics></math>w←w−αv/(1−α2​)<svg xmlns="http://www.w3.org/2000/svg" width='400em' height='1.28em' viewBox='0 0 400000 1296' preserveAspectRatio='xMinYMin slice'><path d='M263,681c0.7,0,18,39.7,52,119
c34,79.3,68.167,158.7,102.5,238c34.3,79.3,51.8,119.3,52.5,120
c340,-704.7,510.7,-1060.3,512,-1067
l0 -0
c4.7,-7.3,11,-11,19,-11
H40000v40H1012.3
s-271.3,567,-271.3,567c-38.7,80.7,-84,175,-136,283c-52,108,-89.167,185.3,-111.5,232
c-22.3,46.7,-33.8,70.3,-34.5,71c-4.7,4.7,-12.3,7,-23,7s-12,-1,-12,-1
s-109,-253,-109,-253c-72.7,-168,-109.3,-252,-110,-252c-10.7,8,-22,16.7,-34,26
c-22,17.3,-33.3,26,-34,26s-26,-26,-26,-26s76,-59,76,-59s76,-60,76,-60z
M1001 80h400000v40h-400000z'/></svg>​+ϵm/(1−α1​)​,
(Fill in the blank) The small factor <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>ϵ</mi></mrow><annotation encoding="application/x-tex">\epsilon</annotation></semantics></math>ϵ is added to prevent possible ___________.

**(Fill in the blank)** The Hessian allows much larger learning rate parameters that ____________ learning.

(Fill in the blank) The Hessian allows much larger learning rate parameters that ____________ learning.

**(Fill in the blank)** In early stopping, we simply monitor the difference between the training and validation error and stop training when they start to ________.

(Fill in the blank) In early stopping, we simply monitor the difference between the training and validation error and stop training when they start to ________.

**(Fill in the blank)** The batch algorithm guarantees that the average training error ________.

(Fill in the blank) The batch algorithm guarantees that the average training error ________.

In $\text{XOR}$, for which two inputs$(x,y)$ will the output be $0$?

In <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>XOR</mtext></mrow><annotation encoding="application/x-tex">\text{XOR}</annotation></semantics></math>XOR, for which two inputs<math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>x</mi><mo separator="true">,</mo><mi>y</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(x,y)</annotation></semantics></math>(x,y) will the output be <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>0</mn></mrow><annotation encoding="application/x-tex">0</annotation></semantics></math>0?

Test yourself on regression and optimization.

Getting started

Introduction

Scientific Programming with Python

Machine Learning with Sklearn

Neural Networks and Keras

Regression and Optimization

Basic Probability Theory

Probabilistic Regression and Bayes Nets

Generative Models

Cyclic Models and Recurrent Neural Networks

Reinforcement Learning

Artificial intelligence, the Brain, and Our Society

Conclusion

Quiz