0x010088F6312065A70A44B630A6848498EAD80093CFEAFE161DC94D83C7C5C9A5A748B8

The course presents theortical concepts of machine learning with a large number of excercies deisgned in google colab to enable students to get hands-on. The course focus on data preprocessing, feature engineering, dimensionality reduction, model selection, and validation. Students learn how to develop their ML piepline, ensemble learning, shallow and deep learning models, transfer learning and more. students use a large set of benchmark datasets and encourged to use real life data in their course projects. This course has not been given due to the few number of students that signed up for it.

The course has not been offered due to few number of students that have signed up for it.

NTNU:TIA:REST

Department of ICT and Natural Sciences

Institutt for IKT og realfag

Engelsk

Mer om vurdering

Portfolio assessment in terms of project(s) report and presentation. Apart from academic excellence, presentation skills are also important and will be evaluated. Ensure that the work submitted is clearly laid out and has legible figures, drawings, and diagrams. Report layout will be decided during the course. A basic report layout consists of an introduction where you summarize the state-of-the-art in this area and give a brief summary of your work. methodology, results, concluding remarks and a reference list. It is worth noting that it is a good habit of adding references wherever needed. The final portfolio will be graded with a letter grade.

Anbefalte forkunnskaper

Basic knowledge of linear algebra and basic knowledge in Python.

Faglig innhold

This course has the aim of providing the foundations of deep learning with the most popular python libraries such as Sklearn, Keras and PyTorch. You will learn the key concepts underlying deep learning and how to use Python to develop machine learning pipelines to tackle real world problems using images, videos, text and time-series. This course will cover convolutional neural networks (CNN), recurrent neural networks (RNN), various advanced CNN architectures, and transfer learning.

Kursmateriell

A reading list will be continuedly updated before the start date of the course. To name a few:<ol><li>Josh Patterson and Adam Gibson (2017). Deep learning: a practitioner’s approach. O'Reilly.</li><li>Andreas C. Muller and Sarah Guido (2017). Introduction to machine learning with python. O'Reilly.</li></ol>

Læringsutbytte

Upon Completion of This Course, You'll Have:<ol><li>An understanding of the capabilities and limitations of machine learning (ML), and the knowledge of how to formulate your problem to solve it effectively.</li><li>An understanding of convolution neural nets, recurrent neural nets, and state-of-the-art transfer learning models.</li><li>An effective process for developing your machine learning pipeline to tackle real world problems such as machine vision, text understanding and time series prediction.</li><li>The skills required to deploying, monitoring, and evaluating the ML model, as well as assessing its relevance, and the uses of different ML models.</li><li>The basis required to collect, process, and utilize data efficiently.</li><li>The basic skills required to select the right platform to deploy your model (cloud, edge device, hybrid) and how to configure it to achieve the required performance.</li><li>The ability to document and communicate the results of your ML approach and guide your coding and ML efforts in the right direction.</li></ol>

Læringsformer og aktiviteter

<ul><li>The course will be offered in approximately 12 weeks (physically and digitally).</li><li>Teaching approach: 5 hours each (lectures - practice - project work).</li><li>Evaluation: exam will be in the form of a portfolio assessment where samples of work and mini projects will be used to evaluate the intended learning outcomes (ILOs) achievement throughout the course.</li><li>Participants will get a certificate of course completion.  </li></ul>

Advanced Deep Learning with Python

Datateknikk og informasjonsvitenskap

Etter- og videreutdanning, IIR

Diverse studier - Fakultet for informasjonsteknologi og elektronikk

Web/Lists(guid'8b698a2d-6ad0-4f7d-b3be-219cc1979f02')/Items(16861)/FieldValuesAsText

Advanced Deep Learning with Python - IE600320