Fundamentals of machine learning (5 op)

Arviointiasteikko

1-5

Osaamistavoitteet

The student: - is familiar with the machine learning engineer role of information systems in industry. - understands the features of machine learning to apply on real world problems. - understands the mathematical foundations behind the machine learning algorithms as well as the paradigms supervised and unsupervised learning. - is able to choose and tune the appropriate machine learning models on existing real life problems. - possesses skills in using the off-the-shelf machine learning tools. Designing timely and efficient algorithms in a range of real-world applications. - understanding of the strengths and weaknesses of many popular machine learning approaches. - is able to design and implement various machine learning algorithms in a range of real-world applications.

Sisältö

Main contents of the course: - Supervised learning, knn algorithm as an example - Unsupervised learning, k-means algorithm as an example - Quantitative variables/data, standard deviation, covariance, correlation - Linear Regression - Topic detection, regular expressions - Natural Language Processing - Sentiment Analysis

Aika ja paikka

Studying mainly takes place online.

Oppimateriaalit

The course utilizes Learn as the primary learning management system, with Zoom for live communications and discussions. For implementing assignments and projects, proficiency in Python within a Jupyter Notebook or Visual Studio Code (VSCode) environment is required. Below is a list of recommended textbooks and software tools to support your learning journey: • "Introduction to Machine Learning with Python" by Andreas C. Müller & Sarah Guido - This book provides a practical introduction to machine learning with Python, covering the use of the scikit-learn library. It is particularly useful for understanding supervised and unsupervised learning paradigms. • "Pattern Recognition and Machine Learning" by Christopher M. Bishop - Offers an in-depth look into the mathematical foundations behind machine learning algorithms, suitable for students who wish to go deeper into the subject. • "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville - While primarily focused on deep learning, this book provides foundational knowledge applicable to all areas of machine learning. Software Tools: Python Libraries: Essential for practical exercises and projects. Key libraries include: • Scikit-learn for general machine learning tasks. • Pandas and NumPy for data manipulation and numerical computations. • Matplotlib and Seaborn for data visualization. • NLTK for natural language processing tasks.

Opetusmenetelmät

The course incorporates several practice assignments and a project completed individually. Before completing these projects, students will attend lectures on Zoom or watch videos focused on machine learning techniques and the use of Python libraries, complemented by small exercises to solidify their understanding. This approach ensures that students are well-prepared to tackle the practical challenges posed by the assignments and project. This course offers a comprehensive introduction to the fundamental concepts, methodologies, and tools essential for gaining a solid understanding of machine learning. Through this course, students will become acquainted with the critical role of Machine Learning Engineers in industry settings. By the end of this course, participants will be equipped to: • Recognize and articulate the core responsibilities and expertise necessary for a Machine Learning Engineer. • Understand and apply the key features of machine learning to tackle real-world problems. • Grasp the mathematical underpinnings of machine learning algorithms, including both supervised and unsupervised learning paradigms. • Select and fine-tune suitable machine learning models for practical applications. • Acquire proficiency in utilizing readily available machine learning tools and designing efficient, timely algorithms for diverse real-world scenarios. • Evaluate the advantages and limitations of various well-known machine learning strategies. • Design and execute various machine learning algorithms tailored to specific real-world applications. Through a combination of online zoom sessions, video lectures, hands-on labs, and project-based learning, students will explore topics such as: • Supervised and unsupervised learning • Quantitative analysis (Quantitative variables/data, standard deviation, covariance, correlation) • Linear regression • Topic detection • Natural language processing • Sentiment analysis. This curriculum is designed to not only provide theoretical knowledge but also to offer practical experience in applying machine learning techniques to real-life challenges.

Opiskelijan ajankäyttö ja kuormitus

Completing one credit point means approximately 27 hours of student work.