- Identify and explain fundamental techniques of signal processing
- Identify and explain fundamental techniques of machine learning
- Identify and explain fundamental techniques of image processing analysis
- Identify and explain fundamental techniques of text analysis
- Identify and explain fundamental techniques of speech analysis
- Identify and explain fundamental techniques of computational finance
- Identify and explain fundamental techniques of bioinformatics
- Identify and explain fundamental techniques of complex networks
Forms of Teaching
Lectures take place in a lecture room with a lecturer who is an expert on a specific subject. The lecture is interactive, and students are expected to participate in the discussion.Laboratory
Laboratory exercises are held in labs equipped with computers. During the exercise, students try out theoretical concepts and apply them to specific problems
|Type||Threshold||Percent of Grade||Threshold||Percent of Grade|
|Laboratory Exercises||0 %||20 %||0 %||0 %|
|Mid Term Exam: Written||50 %||40 %||0 %|
|Final Exam: Written||50 %||40 %|
|Exam: Written||50 %||100 %|
Week by Week Schedule
- Problem definition.
- Advantages and drawbacks.
- Machine learning tasks and applications; Machine learning approaches and paradigms; Hypothesis, model, parameter space, version space.
- Inductive learning and inductive bias, language and preference bias; Loss function and error function; Overfitting and model selection, empirical and structural risk minimization.
- Perceptron (learning paradigms,Hebbian learning, competitive learning, Boltzmann learning); Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time); Self-organizing networks (Hebbian non-supervised learning, Oja's learning rule, PCA using self-organizing network, Sanger's learning rule, Competitive non-supervised learning, winner-takes-all network, Kohonen's self-organizing maps); Radial basis function networks (solving interpolation problem with radial basis function networks, generalized radial basis function networks, relation to regularization theory).
- Recurrent neural networks (Hopfield network, Hopfield network energy function, Boltzman machine, Elman networks, Jordan networks) and learning algorithms (back propagation through time, reccurent backpropagation); Network ensembles (committee machines, mixture of experts, convolutional neural networks); Spike neuron model and spiking neural network.
- Parametric models; Parameter estimation; Speech feature vectors; Cepstral analysis; Hommomorphic analysis.
- Midterm exam.
- Definition; Terms; Examples of real-world networks and their properties.
- Classification in computational finance; Modelling in computational finance.
- Document classification and tagging; Document clustering; Text information extraction (named entities, keyphrases, relations, etc;); Event detection and tracking; Document summarization, multidocument summarization; Latent semantic document models (LSI, LDA); Textual similarity, paraphrase, and entailment.
- Light and EM spectrum; Human visual system; Image sampling and quantization; Discrete geometry; 2D linear systems; Image sensors; Basic image processing operations; Application areas.
- Problem definition; Feature extraction; Image segmentation; Texture analysis; Shape analysis; Motion analysis.
- Protein, RNA and DNA; Biological sequences and structures; Bioinformatics databases; Data formats.
- Final exam.