10 summer courses for machine learning
Over the past decades, self-driving cars, speech recognition systems, and efficient search have been created using machine learning. Now it is one of the most rapidly developing and promising areas at the junction of computer science and statistics, which is actively used in artificial intelligence and data science. Machine learning methods are used in science, technology, medicine, retail, advertising, multimedia generation and other fields.
The ITMO University team gathered ten machine learning courses that can be completed before the end of the summer. One they will help to enter the profession, and others - to go deep into it.
1. “Introduction to Machine Learning”
Area: Coursera
Author: Higher School of Economics, School of Data Analysis Yandex
Duration: 7 weeks, 3-5 hours per week
Cost: Free
Language: Russian
The course tells mainly about the main types of machine learning tasks: classification , regression and clustering. Teachers from Yandex and the Higher School of Economics explain the basic methods and tell about their features, teach them to evaluate the quality of the models and to understand which problem each of them is suitable for. The program is designed for seven weeks, but if you try, you can finish the course before September 1. The course is aimed at students who are familiar with Python, as its numpy, pandas and scikit-learn libraries are used.
2. Introduction to machine learning from GL4G
Area: Great Learning
Author: Great Learning
Duration: 1.5 hours
Cost: Free
Language: English The
short course is designed for those interested in machine learning, but for the time being does not know where to start. The program consists of 12 video lessons and explains what machine learning is and how an algorithm can learn, tells basic terminology and methods, and also gives practical exercises.
3. Machine learning from A to Z: the use of Python and R in data science.
Site: Udemy
Author: Kirill Eremenko ,, Hadelin de Ponteves, SuperDataScience team
Duration: 41 hours of video lectures
Cost: $ 10.99
Language: English
The course was developed by two data scientists to explain complex theory, algorithms, and programming using machine learning libraries. The program consists of ten parts, which deals with data processing, regression, classification, clustering, reinforcement learning, natural language processing, and deep learning. The course has practical exercises and code templates for Python and R. Much attention is paid to choosing the right model for each type of task.
4. Bootcamp Training: Python for Data Science and Machine Learning
Area: Udemy
Author: José Portilla
Duration: 21.5 hours of video lectures
Cost: $ 10.99
Language: English
The course program helps you understand how to use Python to analyze data, create visualizations and use machine learning algorithms. The course uses NumPy, Seaborn, Matplotlib, Pandas, Scikit-Learn, Machine Learning, Plotly, Tensorflow, and other tools. Also, students will be told about the processing of natural language, artificial intelligence and deep learning.
5. Data science, deep learning and machine learning with Python.
Platform: Udemy
Author: Frank Kane
Duration: 12 hours of video lectures
Cost: $ 10.99
Language: English
The course covers the use of artificial intelligence and machine learning to solve business problems. Lecturer Frank Kane worked for nine years at Amazon and IMDb, creating recommendation systems. Each concept is described in simple language without complex mathematical terms. After the introductory part, the use of Python code is demonstrated. The focus is on practical understanding and application of machine learning algorithms. At the end of the course, students are offered work on a final project in order to apply new knowledge.
6. Machine learning course from Google
Platform: Google
Author: Google
Duration: 15 hours of video lectures
Cost: free
Language: English
The company offers a quick and practical introduction to machine learning using the TensorFlow API. The course includes a series of lessons with video lectures, real-life tasks and practical exercises. In total, students need to listen to 25 lessons and perform 40 exercises. Interactive visualization is offered for all algorithms.
7. Structuring Machine Learning Projects
Site: Coursera
Author: deeplearning.ai
Duration: two weeks
Cost: Subscription to Coursera $ 32 per month
Language: English
Stanford University course instructors will tell you how to build a machine learning team job. In two weeks, students will learn to find errors in the machine learning system, set priorities in the direction of work, and understand complex parts of machine learning, for example, invalid learning data sets.
8. Using deep learning in creativity with the help of TensorFlow
Area: Kadenze
Author: Google Magenta
Duration: five sessions of 12 hours
Cost: free
Language: English, Russian subtitles
The course was created with the support of Google's Magenta project, in which the company is trying to create a “creative computer”. Teachers talk about the main components of deep learning, which are necessary for building algorithms: convolutional networks, variational autocoders, generative adversarial networks, and recursive neural networks. Attention is paid to the creativity of neural networks. For example, working with an image and creating content that will fit the aesthetics or content of another image.
9. Statistical machine learning
Site: YouTube
Author: Carnegie Mellon University
Duration: 24 lectures of 1.5 hours
Cost: free
Language: English, Russian subtitles
On YouTube, there is a recording of a series of lectures by the professor of the Department of Statistics and the Faculty of Machine Learning at Carnegie Mellon University Larry Wasserman. The course is designed for people with advanced knowledge of mathematics and programming, as it focuses on the integration of statistics and machine learning. The prerequisites for the course are the lectures “Intermediate Statistical Theory” and “Introduction to Machine Learning” .
10. “Principles of machine learning”
Area: EdX
Author: Microsoft
Duration: 6 weeks, 2–4 hours per week
Price: free, certificate $ 99
Language: English
The course is included in the certification of Microsoft in the field of data science. It tells you how to create and work with machine learning models using Python, R and Azure Machine Learning. Teachers talk about classification, regression in machine learning, controlled models, non-linear modeling systems, clustering, and the development of recommendations.
For those who are closer to offline meetings, ITMO University from August 2 to 15 will hold the Summer Machine Learning School in St. Petersburg based on the Center for Speech Technologies. Students will gain practical experience in applying deep learning methods and algorithms for analyzing audiovisual data for emotion recognition.
Requirements for participants:
- senior students;
- possession of Python;
- have experience in applying modern methods of machine learning;
- a great desire to develop in the field of audio and video analytics.
Accepting applications will last until July 23. You can register online. Participation in the school is free. Also, the organizers pay for accommodation in the hostel of ITMO University. And for the best solution of the test task - and transportation costs.
The ITMO University team gathered ten machine learning courses that can be completed before the end of the summer. One they will help to enter the profession, and others - to go deep into it.
1. “Introduction to Machine Learning”
Area: Coursera
Author: Higher School of Economics, School of Data Analysis Yandex
Duration: 7 weeks, 3-5 hours per week
Cost: Free
Language: Russian
The course tells mainly about the main types of machine learning tasks: classification , regression and clustering. Teachers from Yandex and the Higher School of Economics explain the basic methods and tell about their features, teach them to evaluate the quality of the models and to understand which problem each of them is suitable for. The program is designed for seven weeks, but if you try, you can finish the course before September 1. The course is aimed at students who are familiar with Python, as its numpy, pandas and scikit-learn libraries are used.
2. Introduction to machine learning from GL4G
Area: Great Learning
Author: Great Learning
Duration: 1.5 hours
Cost: Free
Language: English The
short course is designed for those interested in machine learning, but for the time being does not know where to start. The program consists of 12 video lessons and explains what machine learning is and how an algorithm can learn, tells basic terminology and methods, and also gives practical exercises.
3. Machine learning from A to Z: the use of Python and R in data science.
Site: Udemy
Author: Kirill Eremenko ,, Hadelin de Ponteves, SuperDataScience team
Duration: 41 hours of video lectures
Cost: $ 10.99
Language: English
The course was developed by two data scientists to explain complex theory, algorithms, and programming using machine learning libraries. The program consists of ten parts, which deals with data processing, regression, classification, clustering, reinforcement learning, natural language processing, and deep learning. The course has practical exercises and code templates for Python and R. Much attention is paid to choosing the right model for each type of task.
4. Bootcamp Training: Python for Data Science and Machine Learning
Area: Udemy
Author: José Portilla
Duration: 21.5 hours of video lectures
Cost: $ 10.99
Language: English
The course program helps you understand how to use Python to analyze data, create visualizations and use machine learning algorithms. The course uses NumPy, Seaborn, Matplotlib, Pandas, Scikit-Learn, Machine Learning, Plotly, Tensorflow, and other tools. Also, students will be told about the processing of natural language, artificial intelligence and deep learning.
5. Data science, deep learning and machine learning with Python.
Platform: Udemy
Author: Frank Kane
Duration: 12 hours of video lectures
Cost: $ 10.99
Language: English
The course covers the use of artificial intelligence and machine learning to solve business problems. Lecturer Frank Kane worked for nine years at Amazon and IMDb, creating recommendation systems. Each concept is described in simple language without complex mathematical terms. After the introductory part, the use of Python code is demonstrated. The focus is on practical understanding and application of machine learning algorithms. At the end of the course, students are offered work on a final project in order to apply new knowledge.
6. Machine learning course from Google
Platform: Google
Author: Google
Duration: 15 hours of video lectures
Cost: free
Language: English
The company offers a quick and practical introduction to machine learning using the TensorFlow API. The course includes a series of lessons with video lectures, real-life tasks and practical exercises. In total, students need to listen to 25 lessons and perform 40 exercises. Interactive visualization is offered for all algorithms.
7. Structuring Machine Learning Projects
Site: Coursera
Author: deeplearning.ai
Duration: two weeks
Cost: Subscription to Coursera $ 32 per month
Language: English
Stanford University course instructors will tell you how to build a machine learning team job. In two weeks, students will learn to find errors in the machine learning system, set priorities in the direction of work, and understand complex parts of machine learning, for example, invalid learning data sets.
8. Using deep learning in creativity with the help of TensorFlow
Area: Kadenze
Author: Google Magenta
Duration: five sessions of 12 hours
Cost: free
Language: English, Russian subtitles
The course was created with the support of Google's Magenta project, in which the company is trying to create a “creative computer”. Teachers talk about the main components of deep learning, which are necessary for building algorithms: convolutional networks, variational autocoders, generative adversarial networks, and recursive neural networks. Attention is paid to the creativity of neural networks. For example, working with an image and creating content that will fit the aesthetics or content of another image.
9. Statistical machine learning
Site: YouTube
Author: Carnegie Mellon University
Duration: 24 lectures of 1.5 hours
Cost: free
Language: English, Russian subtitles
On YouTube, there is a recording of a series of lectures by the professor of the Department of Statistics and the Faculty of Machine Learning at Carnegie Mellon University Larry Wasserman. The course is designed for people with advanced knowledge of mathematics and programming, as it focuses on the integration of statistics and machine learning. The prerequisites for the course are the lectures “Intermediate Statistical Theory” and “Introduction to Machine Learning” .
10. “Principles of machine learning”
Area: EdX
Author: Microsoft
Duration: 6 weeks, 2–4 hours per week
Price: free, certificate $ 99
Language: English
The course is included in the certification of Microsoft in the field of data science. It tells you how to create and work with machine learning models using Python, R and Azure Machine Learning. Teachers talk about classification, regression in machine learning, controlled models, non-linear modeling systems, clustering, and the development of recommendations.
For those who are closer to offline meetings, ITMO University from August 2 to 15 will hold the Summer Machine Learning School in St. Petersburg based on the Center for Speech Technologies. Students will gain practical experience in applying deep learning methods and algorithms for analyzing audiovisual data for emotion recognition.
Requirements for participants:
- senior students;
- possession of Python;
- have experience in applying modern methods of machine learning;
- a great desire to develop in the field of audio and video analytics.
Accepting applications will last until July 23. You can register online. Participation in the school is free. Also, the organizers pay for accommodation in the hostel of ITMO University. And for the best solution of the test task - and transportation costs.