TIES4910 Deep-Learning for Cognitive Computing, Theory (5 cr)
Description
Content
The course Deep Learning for Cognitive Computing (10 credits, delivered in English) is an evolution of the course ITKA-352: “Introduction to Watson Technologies”, which aims to provide more systematic, structured (broader, deeper and multidisciplinary) view to this popular domain. The major objectives of the course are as follows:
· To describe challenges and opportunities within the emerging Cognitive Computing domain and professions around it;
· To summarize role and relationships of Cognitive Computing within the network of closely related scientific domains, professional fields and courses of the faculty (e.g., Artificial Intelligence, Semantic and Agent Technologies, Big Data Analytics, Semantic Web and Linked Data; Cloud Computing, Internet of Things, etc.);
· To introduce the major providers of cognitive computing services (Intelligence-as-a-Service) on the market (e.g., IBM Watson, Google DeepMind, Microsoft Cognitive Services, etc.) and show demos of their services (e.g., text, speech, image, sentiment, etc., processing, analysis, recognition, diagnostics, prediction, etc.);
· To give introduction on major theories, methods and algorithms used within cognitive computing services with particular focus on Deep Learning technology;
· To provide “friendly” (with reasonable amount of mathematics) introduction to Deep Learning (including variations of deep Neural Networks and approaches to train them);
· To provide different views to this knowledge suitable to people with different backgrounds and study objectives (ordinary user, advanced user, software engineer, domain professional, data scientist, cognitive analyst, mathematician, etc.);
· To discuss scientific challenges and open issues within the domain as well as to share with the students information on relevant ongoing projects in the Faculty;
· To train within teams to use available cognitive services via GUIs or APIs for inventing new interesting use cases and designing own applications;
· For advanced students there will be a possibility to contribute (enhance, optimize, etc.) known algorithms or the related science behind them.
We believe that knowledge on Cognitive Computing at least at the level of an advanced user of it would be an excellent added value within the portfolio of every professional (from very humanitarian to very technical one).
We will combine overview lectures, self-study, group-work, theoretical and practical assignments trying to find an optimal approach to everyone.
Completion methods
Assignment
Assessment details
Look for details here (http://www.cs.jyu.fi/ai/vagan/DL4CC.html)
Look for details here (http://www.cs.jyu.fi/ai/vagan/DL4CC.html)
Learning outcomes
Understanding of the Deep Learning "philosophy";
Knowledge on Neural Nets and Deep Neural Nets (Recurrent, Convolutional, etc.) and their learning approaches;
Capability to utilize Cognitive Computing services (from IBM , Google, Microsoft, etc.) as an advanced user
Additional information
Look for details here (http://www.cs.jyu.fi/ai/vagan/DL4CC.html)
Links
Description of prerequisites
Study materials
· Part I. (Lectures 1-3):
o Topic: Cognitive Computing: Intelligence-as-a-Service (IBM Watson, Google’s Deep Mind & Microsoft Cognitive Services)
o See the lecture slides (http://www.cs.jyu.fi/ai/vagan/DL4CC_Part-1.pptx ; download before viewing and switch on speakers).
o Our concerns within the Part-I:
- Why and what is Cognitive Computing;
- Why to study;
- Cognitive Computing as a context for other technologies (e.g., Semantic and Agent Technologies, IoT, Industry 4.0, etc.);
- What is available on the market of “Intelligence-as-a-Service” for users and developers (from IBM Watson, DeepMind / Google, Cognitive Services of Microsoft, etc.);
- How all these related to “Deep Learning”.
· Part II. (Lectures 4-6):
o Topic: Introduction to Neural Networks and Deep Learning
o See the lecture slides (http://www.cs.jyu.fi/ai/vagan/DL4CC_Part-2.pptx ; download before viewing).
o Our concerns within the Part-II:
- Deep Learning for beginners;
- Neural nets basics;
- Gradient descent and backpropagation;
- Variations of deep learning approaches and architectures.
· Part III. (Lectures 7-8):
o Topic: Convolutional Neural Networks for Image Processing
o See the lecture slides ( http://www.cs.jyu.fi/ai/vagan/DL4CC_Part-3.pptx; download before viewing).
o Our concerns within the Part-III:
- What is Convolutional Neural Network and how it works;
- What kind of architecture has a Convolutional Neural Network;
- How a Convolutional Neural Network processes images;
- How to train a Convolutional Neural Network.
· Part IV. (Lectures 9-10):
o Topic: Neural Networks with Memory: Recurrent Neural Networks and LSTM Networks
o See the lecture slides ( http://www.cs.jyu.fi/ai/vagan/DL4CC_Part-4.pptx; download before viewing).
o Our concerns within the Part-IV:
- What is Recurrent Neural Network (RNN) and how it works;
- What is Long Short-Term Memory (LSTM) network and how it works;
- How they are used;
- How to train a RNN and LSTM.
Literature
- http://www.deeplearningbook.org
- http://neuralnetworksanddeeplearning.com/
- Deep Learning Resources (http://deeplearning.net/)
- http://deeplearning.net/
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning, MIT Press, 787 pp. (http://www.deeplearningbook.org)
- Michael Nielsen (2017). Neural Networks and Deep Learning. (http://neuralnetworksanddeeplearning.com/)