DD2437 Artificial Neural Networks and Deep Architectures 7.5 credits

Artificiella neuronnät och djupa arkitekturer

  • Education cycle

    Second cycle
  • Main field of study

    Computer Science and Engineering
    Information Technology
  • Grading scale

    A, B, C, D, E, FX, F

Course offerings

Autumn 18 SAP for Study Abroad Programme (SAP)

  • Periods

    Autumn 18 P1 (7.5 credits)

  • Application code

    10115

  • Start date

    27/08/2018

  • End date

    26/10/2018

  • Language of instruction

    English

  • Campus

    KTH Campus

  • Tutoring time

    Daytime

  • Form of study

    Normal

  • Number of places

    No limitation

  • Target group

    Only open for students within the SAP-programme.

  • Application

    Apply for this course at antagning.se through this application link.
    Please note that you need to log in at antagning.se to finalize your application.

Spring 19 annda18 for programme students

  • Periods

    Spring 19 P3 (7.5 credits)

  • Application code

    60747

  • Start date

    15/01/2019

  • End date

    15/03/2019

  • Language of instruction

    English

  • Campus

    KTH Campus

  • Tutoring time

    Daytime

  • Form of study

    Normal

  • Number of places

    No limitation

  • Course responsible

    Erik Fransén <erikf@kth.se>

    Pawel Herman <paherman@kth.se>

  • Teacher

    Pawel Herman <paherman@kth.se>

  • Target group

    Searchable for students from year 3 and for students admitted to a master programme.

Spring 18 annda18 for programme students

Spring 18 for Study Abroad Programme (SAP)

  • Periods

    Spring 18 P3 (7.5 credits)

  • Application code

    20018

  • Start date

    16/01/2018

  • End date

    17/03/2018

  • Language of instruction

    English

  • Campus

    KTH Campus

  • Tutoring time

    Daytime

  • Form of study

    Normal

  • Number of places

    No limitation

  • Target group

    Only open för students within Study Abroad Programme (SAP)

Intended learning outcomes

After completing the course the student should be able to

  • describe the structure and function of the most common artificial neural network (ANN) types, e.g. multi-layer perceptron, recurrent network, self-organizing maps, Boltzmann machine, deep belief network, autoencoder, and provide examples of their applications
  • explain mechanisms of supervised/unsupervised learning from data and information processing in different ANN architectures, and also account for derivations of the basic ANN algorithms discussed in the course
  • demonstrate when and how deep architectures lead to increased performance in pattern recognition and data mining problems
  • quantitatively analyse the process and outcomes of learning in ANNs, and account for their shortcomings, limitations
  • apply, validate and evaluate suggested types of ANNs in typical small problems in the realm of regression, prediction, pattern recognition, scheduling and optimisation
  • devise and implement ANN approaches to selected problems in pattern recognition, system identification or predictive analytics using commonly available development tools, and critically examine their applicability

in order to

  • obtain an understanding of the technical potential as well as advantages and limitations of today's learning, adaptive and self-organizing systems,
  • acquire the ANN practitioner’s competence to apply and develop ANN based solutions to data analytics problems.

Course main content

The course is concerned with computational problems in massively parallel artificial neural network (ANN) architectures, which rely on distributed simple computational nodes and robust learning algorithms that iteratively adjust the connections between the nodes heavily using the available data samples. The learning rule and network architecture determine specific computational properties of the ANN. The course offers an opportunity to develop the conceptual and theoretical understanding of computational capabilities of ANNs starting from simpler systems and progressively studying more advanced architectures, and hence exploring the breadth of learning types – from strictly supervised to purely explorative unsupervised mode. The course content therefore includes among others multi-layer perceptrons (MLPs), self-organising maps (SOMs), Boltzmann machines, Hopfield networks and state-of-the-art deep neural networks (DNNs) along with the corresponding learning algorithms. An important objective of the course is for the students to gain practical experience of selecting, developing, applying and validating suitable networks and algorithms to effectively address a broad class of regression, classification, temporal prediction, data modelling, explorative data analytics or clustering problems. Finally, the course provides revealing insights into the principles of generalisation capabilities of ANNs, which underlie their predictive power.

Eligibility

Recommended prerequisites

The mandatory courses in mathematics, numerical analysis and computer science for D, E, and F-students or the equivalent.

Literature

[1] Stephen Marsland. Machine Learning, an Algorithmic Perspective, 2009,CSC-Press. 

[2] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning., 2016, MIT press.

Additional recommended reading will be announced on the course website. 

Examination

  • LAB2 - Laboratory assignments, 4.0, grading scale: P, F
  • TEN2 - Examination, 3.5, grading scale: A, B, C, D, E, FX, F

Offered by

CSC/computational Science and Technology

Contact

Pawel Herman e-post: paherman@kth.se

Examiner

Erik Fransén <erikf@kth.se>

Pawel Herman <paherman@kth.se>

Version

Course syllabus valid from: Spring 2018.
Examination information valid from: Spring 2018.