Opetussuunnitelmat

Objective

The student understands the significance of deep learning in the digitalizing operational environment and knows the type and structure of neural network.

The student knows about the most common methods of deep learning and how to desing and apply them in practice to the data and interpret the results of the methods. In addition, the student undestands the mathematic behind the neural networks.

Course competences:
EUYIV EUR-ACE: Investigations, Master's Degree
EUYER EUR-ACE: Engineering Practice, Master's Degree
EUYMJ EUR-ACE: Making Judgements, Master's Degree

Content

- Structure of neural network vs artificial neural network
- Neural network Architecture
- Different types of neural networks and their applications: CNN, RNN, LSTM, autocorrelation, autoencoder (CAN) etc.
- Mathematic behind the neural network
- Feature engineering
- Training process of neural network
- Loss, Loss functions and Metrics
- Undefitting and Overfitting
- Estimate and interpret the results
- Regularization
- Hyperparameter tuning
- Transfer and Active Learning

Location and time

The course starts on Friday 6.9.2024 at Teams

Mandatory contact days:
Friday 15.11.2024 15.00-20.00
Saturday 16.11.2026 9.00-15.00

Teams Meeting is not available.

Evaluation scale

0-5

Arviointikriteerit, tyydyttävä (1-2)

Sufficient 1: Student has sufficient knowledge of deep learning and neural networks. Student is able to apply the most common techniques of deep learning and has the sufficient knowledge of mathematic behind the technigues. Additionally, the student is able to estimate and validate implementation briefly.

Satisfactory 2: Student has satisfied knowledge of deep learning and neural networks. Student is able to choose suitable deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in satisfying level. Additionally, the student is able to estimate and validate implementation superficially.

Arviointikriteerit, hyvä (3-4)

Good 3: Student has good knowledge of deep learning and neural networks. Student is able to choose appropriate deep learning tehnique and apply the technical know-how in practise. Student undestands well the mathematic behind the technigues in good level. Additionally, the student is able to estimate and validate implementation well.

Very good 4: Student has very good knowledge of deep learning and neural networks. Student is able to choose and justify versatilely deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in very good level. Additionally, the student is able to estimate and validate implementation critically.

Assessment criteria, excellent (5)

Excellent 5: Student has excellent knowledge of deep learning and neural networks. Student is able to choose and justify deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in excellent level. Additionally, the student is able to estimate and validate implementation critically.

Objective

The student understands the significance of deep learning in the digitalizing operational environment and knows the type and structure of neural network.

The student knows about the most common methods of deep learning and how to desing and apply them in practice to the data and interpret the results of the methods. In addition, the student undestands the mathematic behind the neural networks.

Course competences:
EUYIV EUR-ACE: Investigations, Master's Degree
EUYER EUR-ACE: Engineering Practice, Master's Degree
EUYMJ EUR-ACE: Making Judgements, Master's Degree

Content

- Structure of neural network vs artificial neural network
- Neural network Architecture
- Different types of neural networks and their applications: CNN, RNN, LSTM, autocorrelation, autoencoder (CAN) etc.
- Mathematic behind the neural network
- Feature engineering
- Training process of neural network
- Loss, Loss functions and Metrics
- Undefitting and Overfitting
- Estimate and interpret the results
- Regularization
- Hyperparameter tuning
- Transfer and Active Learning

Location and time

Mandatory contacts days:

Friday 8.9.2023 15.00-20.00
Saturday 11.11.2023 9.00-15.00

Teams Meeting is not available.

Evaluation scale

0-5

Arviointikriteerit, tyydyttävä (1-2)

Sufficient 1: Student has sufficient knowledge of deep learning and neural networks. Student is able to apply the most common techniques of deep learning and has the sufficient knowledge of mathematic behind the technigues. Additionally, the student is able to estimate and validate implementation briefly.

Satisfactory 2: Student has satisfied knowledge of deep learning and neural networks. Student is able to choose suitable deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in satisfying level. Additionally, the student is able to estimate and validate implementation superficially.

Arviointikriteerit, hyvä (3-4)

Good 3: Student has good knowledge of deep learning and neural networks. Student is able to choose appropriate deep learning tehnique and apply the technical know-how in practise. Student undestands well the mathematic behind the technigues in good level. Additionally, the student is able to estimate and validate implementation well.

Very good 4: Student has very good knowledge of deep learning and neural networks. Student is able to choose and justify versatilely deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in very good level. Additionally, the student is able to estimate and validate implementation critically.

Assessment criteria, excellent (5)

Excellent 5: Student has excellent knowledge of deep learning and neural networks. Student is able to choose and justify deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in excellent level. Additionally, the student is able to estimate and validate implementation critically.

Objective

The student understands the significance of deep learning in the digitalizing operational environment and knows the type and structure of neural network.

The student knows about the most common methods of deep learning and how to desing and apply them in practice to the data and interpret the results of the methods. In addition, the student undestands the mathematic behind the neural networks.

Course competences:
EUYIV EUR-ACE: Investigations, Master's Degree
EUYER EUR-ACE: Engineering Practice, Master's Degree
EUYMJ EUR-ACE: Making Judgements, Master's Degree

Content

- Structure of neural network vs artificial neural network
- Neural network Architecture
- Different types of neural networks and their applications: CNN, RNN, LSTM, autocorrelation, autoencoder (CAN) etc.
- Mathematic behind the neural network
- Feature engineering
- Training process of neural network
- Loss, Loss functions and Metrics
- Undefitting and Overfitting
- Estimate and interpret the results
- Regularization
- Hyperparameter tuning
- Transfer and Active Learning

Location and time

Mandatory contact days:
Sat 10.9.2022 klo 9-15
Fri 18.11.2022 klo 15-20

Evaluation scale

0-5

Arviointikriteerit, tyydyttävä (1-2)

Sufficient 1: Student has sufficient knowledge of deep learning and neural networks. Student is able to apply the most common techniques of deep learning and has the sufficient knowledge of mathematic behind the technigues. Additionally, the student is able to estimate and validate implementation briefly.

Satisfactory 2: Student has satisfied knowledge of deep learning and neural networks. Student is able to choose suitable deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in satisfying level. Additionally, the student is able to estimate and validate implementation superficially.

Arviointikriteerit, hyvä (3-4)

Good 3: Student has good knowledge of deep learning and neural networks. Student is able to choose appropriate deep learning tehnique and apply the technical know-how in practise. Student undestands well the mathematic behind the technigues in good level. Additionally, the student is able to estimate and validate implementation well.

Very good 4: Student has very good knowledge of deep learning and neural networks. Student is able to choose and justify versatilely deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in very good level. Additionally, the student is able to estimate and validate implementation critically.

Assessment criteria, excellent (5)

Excellent 5: Student has excellent knowledge of deep learning and neural networks. Student is able to choose and justify deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in excellent level. Additionally, the student is able to estimate and validate implementation critically.

Objective

The student understands the significance of deep learning in the digitalizing operational environment and knows the type and structure of neural network.

The student knows about the most common methods of deep learning and how to desing and apply them in practice to the data and interpret the results of the methods. In addition, the student undestands the mathematic behind the neural networks.

Course competences:
EUYIV EUR-ACE: Investigations, Master's Degree
EUYER EUR-ACE: Engineering Practice, Master's Degree
EUYMJ EUR-ACE: Making Judgements, Master's Degree

Content

- Structure of neural network vs artificial neural network
- Neural network Architecture
- Different types of neural networks and their applications: CNN, RNN, LSTM, autocorrelation, autoencoder (CAN) etc.
- Mathematic behind the neural network
- Feature engineering
- Training process of neural network
- Loss, Loss functions and Metrics
- Undefitting and Overfitting
- Estimate and interpret the results
- Regularization
- Hyperparameter tuning
- Transfer and Active Learning

Location and time

Hybrid meeting (classroom in Dynamo/Lutakko and Teams).

Oppimateriaali ja suositeltava kirjallisuus

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. The MIT Press.

Teaching methods

2 hybrid meeting during the course.

Evaluation scale

0-5

Arviointikriteerit, tyydyttävä (1-2)

Sufficient 1: Student has sufficient knowledge of deep learning and neural networks. Student is able to apply the most common techniques of deep learning and has the sufficient knowledge of mathematic behind the technigues. Additionally, the student is able to estimate and validate implementation briefly.

Satisfactory 2: Student has satisfied knowledge of deep learning and neural networks. Student is able to choose suitable deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in satisfying level. Additionally, the student is able to estimate and validate implementation superficially.

Arviointikriteerit, hyvä (3-4)

Good 3: Student has good knowledge of deep learning and neural networks. Student is able to choose appropriate deep learning tehnique and apply the technical know-how in practise. Student undestands well the mathematic behind the technigues in good level. Additionally, the student is able to estimate and validate implementation well.

Very good 4: Student has very good knowledge of deep learning and neural networks. Student is able to choose and justify versatilely deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in very good level. Additionally, the student is able to estimate and validate implementation critically.

Assessment criteria, excellent (5)

Excellent 5: Student has excellent knowledge of deep learning and neural networks. Student is able to choose and justify deep learning tehnique and apply the technical know-how in practise. Student undestands the mathematic behind the technigues in excellent level. Additionally, the student is able to estimate and validate implementation critically.