BSc: Nature Inspired Computing - Revision history

M.petrishchev: /* Course grading range */

2022-12-13T08:39:49Z

Course grading range

← Older revision		Revision as of 08:39, 13 December 2022
Line 95:		Line 95:
	\| C. Satisfactory \|\| 60-74 \|\| -		\| C. Satisfactory \|\| 60-74 \|\| -
	\|-		\|-
−	\| D. Poor \|\| 0-55 \|\| -	+	\| D. Poor \|\| 0-59 \|\| -
	\|}		\|}

R.sirgalina: /* Final assessment */

2022-07-12T11:45:26Z

Final assessment

← Older revision		Revision as of 11:45, 12 July 2022
Line 228:		Line 228:
	'''Section 1'''		'''Section 1'''
	# Genetic Algorithms can be used for:		# Genetic Algorithms can be used for:
−	a. Optimization (correct)	+	#:* Optimization (correct)
−	b. Feedback Control	+	#:* Feedback Control
−	c. Automatic Differentiation	+	#:* Automatic Differentiation
−	d. Numeric Geometry	+	#:* Numeric Geometry
	# Applications of evolutionary algorithms do not include		# Applications of evolutionary algorithms do not include
−	a. Robotics	+	#:* Robotics
−	b. Design	+	#:* Design
−	c. Optimization	+	#:* Optimization
−	d. Measurements (correct)	+	#:* Measurements (correct)
	# Which of the following algorithms suffers from local minima of the objective function		# Which of the following algorithms suffers from local minima of the objective function
−	a. Genetic algorithm	+	#:* Genetic algorithm
−	b. Evolutionary algorithm	+	#:* Evolutionary algorithm
−	c. Gradient descent (correct)	+	#:* Gradient descent (correct)
−	d. All three of the above	+	#:* All three of the above
		+
	'''Section 2'''		'''Section 2'''
	# Which of the following are neural networks architectures?		# Which of the following are neural networks architectures?
−	a. ANN, RNN, CNN	+	#:* ANN, RNN, CNN
−	b. RNN, CNN, LSTM	+	#:* RNN, CNN, LSTM
−	c. RNN, CNN, fully connected (correct)	+	#:* RNN, CNN, fully connected (correct)
−	d. Reinforcement learning, Supervised learning	+	#:* Reinforcement learning, Supervised learning
	# Which types of machine learning can be used to learn policies for agents acting in dynamic environments, where marked datasets are not available?		# Which types of machine learning can be used to learn policies for agents acting in dynamic environments, where marked datasets are not available?
−	a. Reinforcement learning, evolutionary algorithms (correct)	+	#:* Reinforcement learning, evolutionary algorithms (correct)
−	b. YOLO	+	#:* YOLO
−	c. Cauterization	+	#:* Cauterization
−	d. Supervised learning	+	#:* Supervised learning
	# What distinguishes deep learning?		# What distinguishes deep learning?
−	a. The number of layers of the network, and the methods of gradient propagation aiming at lowering the effects of the vanishing gradients (correct)	+	#:* The number of layers of the network, and the methods of gradient propagation aiming at lowering the effects of the vanishing gradients (correct)
−	b. Fully-connected layers	+	#:* Fully-connected layers
−	c. LSTM cells	+	#:* LSTM cells
−	d. Auto-encoding layers	+	#:* Auto-encoding layers
		+
	'''Section 3'''		'''Section 3'''
	# Which of the following can be used to solve optimization problems?		# Which of the following can be used to solve optimization problems?
−	a. PSO, Genetic algorithm (correct)	+	#:* PSO, Genetic algorithm (correct)
−	b. CNN, PSO	+	#:* CNN, PSO
−	c. CNN	+	#:* CNN
−	d. RNN, PSO	+	#:* RNN, PSO
	# Which of the following can be used to find acceptable parameters of a process, given inequality constraints?		# Which of the following can be used to find acceptable parameters of a process, given inequality constraints?
−	a. PSO, Genetic algorithm (correct)	+	#:* PSO, Genetic algorithm (correct)
−	b. CNN, PSO	+	#:* CNN, PSO
−	c. CNN	+	#:* CNN
−	d. RNN, PSO	+	#:* RNN, PSO

	=== The retake exam ===		=== The retake exam ===

R.sirgalina at 11:37, 12 July 2022

2022-07-12T11:37:51Z

Show changes

R.sirgalina: /* Course Sections */

2022-07-11T10:20:56Z

Course Sections

← Older revision		Revision as of 10:20, 11 July 2022
Line 127:		Line 127:
	=== Section 1 ===		=== Section 1 ===

−	==== Section title~~: basic concepts of Nature Inspired Computing~~ ====	+	==== Section title ====
		+	Basic concepts of Nature Inspired Computing
−

	==== Topics covered in this section ====		==== Topics covered in this section ====
Line 140:		Line 140:
	*Genetic Programming		*Genetic Programming
	*Symbolic Regression		*Symbolic Regression
−
−

	==== What forms of evaluation were used to test students’ performance in this section? ====		==== What forms of evaluation were used to test students’ performance in this section? ====
Line 186:		Line 184:
	# What are Cellular Automata?		# What are Cellular Automata?
	# Give examples of Evolutionary Algorithms		# Give examples of Evolutionary Algorithms
−

	==== Typical questions for seminar classes (labs) within this section ====		==== Typical questions for seminar classes (labs) within this section ====
Line 194:		Line 191:
	# Write a Genetic Algorithm as a pseudocode		# Write a Genetic Algorithm as a pseudocode
	# What are the characteristics of Genetic Algorithms		# What are the characteristics of Genetic Algorithms
−

	==== Test questions for final assessment in this section ====		==== Test questions for final assessment in this section ====
Line 213:		Line 209:
	#:c. Gradient descent (correct)		#:c. Gradient descent (correct)
	#:d. All three of the above		#:d. All three of the above
−

	=== Section 2 ===		=== Section 2 ===

−	==== Section title~~: Computational complexity, ANN~~ ====	+	==== Section title ====
		+	Computational complexity, ANN
−

	==== Topics covered in this section ====		==== Topics covered in this section ====
Line 234:		Line 229:
	* Self Organizing Maps		* Self Organizing Maps
	* Deep Learning		* Deep Learning
−
−

	==== What forms of evaluation were used to test students’ performance in this section? ====		==== What forms of evaluation were used to test students’ performance in this section? ====
Line 281:		Line 274:
	# What are Recurrent ANN?		# What are Recurrent ANN?
	# What is deep learning?		# What is deep learning?
−

	==== Typical questions for seminar classes (labs) within this section ====		==== Typical questions for seminar classes (labs) within this section ====
Line 289:		Line 281:
	# What is a fully connected ANN?		# What is a fully connected ANN?
	# Draw structure of LSTM RNN		# Draw structure of LSTM RNN
−

	==== Test questions for final assessment in this section ====		==== Test questions for final assessment in this section ====
Line 308:		Line 299:
	#:c. LSTM cells		#:c. LSTM cells
	#:d. Auto-encoding layers		#:d. Auto-encoding layers
−

	=== Section 3 ===		=== Section 3 ===

−	==== Section title~~: Optimization, PSO~~ ====	+	==== Section title ====
		+	Optimization, PSO
−

	==== Topics covered in this section ====		==== Topics covered in this section ====
Line 324:		Line 314:
	* Harmony Search		* Harmony Search
	* Hebbian Learning, Boltzmann Machines		* Hebbian Learning, Boltzmann Machines
−
−
−

	==== What forms of evaluation were used to test students’ performance in this section? ====		==== What forms of evaluation were used to test students’ performance in this section? ====
Line 371:		Line 358:
	# What is a multi-objective optimization?		# What is a multi-objective optimization?
	# What is Ant Colony Optimization?		# What is Ant Colony Optimization?
−
−

	==== Typical questions for seminar classes (labs) within this section ====		==== Typical questions for seminar classes (labs) within this section ====
Line 380:		Line 365:
	# How does the number of particles influence PSO performance?		# How does the number of particles influence PSO performance?
	# How do local minima influence PSO performance?		# How do local minima influence PSO performance?
−
−

	==== Test questions for final assessment in this section ====		==== Test questions for final assessment in this section ====

R.sirgalina: /* Course Objectives Based on Bloom’s Taxonomy */

2022-07-11T10:19:10Z

Course Objectives Based on Bloom’s Taxonomy

← Older revision		Revision as of 10:19, 11 July 2022
Line 28:		Line 28:
	* Basic concepts in Global optimization		* Basic concepts in Global optimization
	* Basic concepts in Classification methods		* Basic concepts in Classification methods
−

	==== What should a student be able to understand at the end of the course? ====		==== What should a student be able to understand at the end of the course? ====
Line 37:		Line 36:
	* Methods of computing computational complexity		* Methods of computing computational complexity
	* Methods of optimization in swarm intelligence		* Methods of optimization in swarm intelligence
−

	==== What should a student be able to apply at the end of the course? ====		==== What should a student be able to apply at the end of the course? ====
Line 48:		Line 46:
	* Co-evolutionary Algorithms		* Co-evolutionary Algorithms
	* Genetic Programming		* Genetic Programming
−

	=== Course evaluation ===		=== Course evaluation ===

R.sirgalina: /* Grades range */

2022-07-11T10:02:12Z

Grades range

← Older revision		Revision as of 10:02, 11 July 2022
Line 91:		Line 91:
	\|align="center"\| 0-55		\|align="center"\| 0-55
	\|}		\|}
		+	</div>

	=== Resources and reference material ===		=== Resources and reference material ===

R.sirgalina: /* Course evaluation */

2022-07-11T10:01:51Z

Course evaluation

← Older revision		Revision as of 10:01, 11 July 2022
Line 70:		Line 70:
	\|align="center"\| 50		\|align="center"\| 50
	\|}		\|}
		+	</div>
−

	=== Grades range ===		=== Grades range ===

M.petrishchev at 13:01, 26 April 2022

2022-04-26T13:01:35Z

← Older revision		Revision as of 13:01, 26 April 2022
Line 19:		Line 19:
	The main purpose of this is to introduce methods and algorithms inspired by naturally occurring phenomena and applying them to optimization, design and learning problems. The course focuses on learning implementation and analysis of such algorithms. These include evolutionary computation, swarm intelligence and neural networks.		The main purpose of this is to introduce methods and algorithms inspired by naturally occurring phenomena and applying them to optimization, design and learning problems. The course focuses on learning implementation and analysis of such algorithms. These include evolutionary computation, swarm intelligence and neural networks.

−	=== Course Objectives Based on Bloom’s Taxonomy ===	+	== Course Objectives Based on Bloom’s Taxonomy ==

	==== What should a student remember at the end of the course? ====		==== What should a student remember at the end of the course? ====

M.petrishchev: M.petrishchev moved page BSc:NatureInspiredComputing to BSc: Nature Inspired Computing

2022-04-18T08:54:28Z

M.petrishchev moved page BSc:NatureInspiredComputing to BSc: Nature Inspired Computing

← Older revision	Revision as of 08:54, 18 April 2022
(No difference)

R.akhmetzyanov: Created page with "= Nature Inspired Computing = * '''Course name:''' Nature Inspired Computing * '''Course number:''' CSE340 == Course characteristics == === Key co..."

2022-04-05T07:47:32Z

Created page with "= Nature Inspired Computing = * <span>'''Course name:'''</span> Nature Inspired Computing * <span>'''Course number:'''</span> CSE340 == Course characteristics == === Key co..."

New page

= Nature Inspired Computing =

* <span>'''Course name:'''</span> Nature Inspired Computing
* <span>'''Course number:'''</span> CSE340

== Course characteristics ==

=== Key concepts of the class ===

* Turing machines, computational complexity
* Approximation algorithms vs heuristics
* Evolutionary Algorithms
* Classification
* Optimization

=== What is the purpose of this course? ===

The main purpose of this is to introduce methods and algorithms inspired by naturally occurring phenomena and applying them to optimization, design and learning problems. The course focuses on learning implementation and analysis of such algorithms. These include evolutionary computation, swarm intelligence and neural networks.

=== Course Objectives Based on Bloom’s Taxonomy ===

==== What should a student remember at the end of the course? ====

By the end of the course, the students should be able to

* Basic concepts in Swarm intelligence concepts
* Basic concepts in Global optimization
* Basic concepts in Classification methods

==== What should a student be able to understand at the end of the course? ====

By the end of the course, the students should be able to

* Computational complexity
* Methods of computing computational complexity
* Methods of optimization in swarm intelligence

==== What should a student be able to apply at the end of the course? ====

By the end of the course, the students should be able to apply:

* Reductions
* Empirical Algorithms
* Evolutionary Algorithms
* Co-evolutionary Algorithms
* Genetic Programming

=== Course evaluation ===

The course has two major forms of evaluations:

<div id="tab:OSCourseGrading">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|+ '''Course grade breakdown'''
!align="center"| '''Component'''
! '''Points'''
|-
| Labs/seminar classes
|align="center"| 20
|-
| Interim performance assessment (class participation)
|align="center"| 30
|-
| Exams
|align="center"| 50
|}

=== Grades range ===

<div id="tab:OSCourseGradingRange">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|+ Course grading range
|-
| A. Excellent
|align="center"| 90-100
|-
| B. Good
|align="center"| 75-89
|-
| C. Satisfactory
|align="center"| 60-74
|-
| D. Poor
|align="center"| 0-55
|}

=== Resources and reference material ===

* '''Textbook:''' Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies, D. Floreano and C. Mattiussi (2008), MIT Press.
* '''Textbook:''' Siddique, N. and Adeli, H., 2015. Nature inspired computing: an overview and some future directions. Cognitive computation, 7(6), pp.706-714.
* '''Textbook:''' Coello, C.C., Dhaenens, C. and Jourdan, L. eds., 2009. Advances in multi-objective nature inspired computing (Vol. 272). Springer.
* '''Textbook:''' Khosravy, M., Gupta, N., Patel, N. and Senjyu, T. eds., 2020. Frontier applications of nature inspired computation. Springer Nature.

== Course Sections ==

The main sections of the course and approximate hour distribution between them is
as follows:

<div id="tab:OSCourseSections">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|+ Course Sections
!align="center"| '''Section'''
! '''Section Title'''
!align="center"| '''Teaching Hours'''
|-
|align="center"| 1
| basic concepts of Nature Inspired Computing
|align="center"| 12
|-
|align="center"| 2
| Computational complexity, ANN
|align="center"| 14
|-
|align="center"| 3
| Optimization, PSO
|align="center"| 10
|}

</div>
=== Section 1 ===

==== Section title: basic concepts of Nature Inspired Computing ====

==== Topics covered in this section ====

*Course Introduction
*Approximation algorithms vs heuristics
*Characteristics of Natural Systems/Algorithms
*Cellular Automata
*Evolutionary Algorithms
*Dynamic Environments
*Genetic Programming
*Symbolic Regression

==== What forms of evaluation were used to test students’ performance in this section? ====

<div id="tab:OSSectionEval1">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|''' '''
! '''Yes/No'''
|-
| Development of individual parts of software product code
|align="center"| 1
|-
| Homework and group projects
|align="center"| 1
|-
| Midterm evaluation
|align="center"| 1
|-
| Testing (written or computer based)
|align="center"| 1
|-
| Reports
|align="center"| 0
|-
| Essays
|align="center"| 0
|-
| Oral polls
|align="center"| 0
|-
| Discussions
|align="center"| 1
|}

</div>

==== Typical questions for ongoing performance evaluation within this section ====

# What is an approximation?
# What is a heuristics?
# What are the main Characteristics of Natural Systems/Algorithms?
# What are Cellular Automata?
# Give examples of Evolutionary Algorithms

==== Typical questions for seminar classes (labs) within this section ====
# Provide an example of approximation?
# What is the difference between Approximation algorithms and heuristics
# Write an Evolutionary Algorithm as a pseudocode
# Write a Genetic Algorithm as a pseudocode
# What are the characteristics of Genetic Algorithms

==== Test questions for final assessment in this section ====

# Genetic Algorithms can be used for:
#:a. Optimization (correct)
#:b. Feedback Control
#:c. Automatic Differentiation
#:d. Numeric Geometry
# Applications of evolutionary algorithms do not include
#:a. Robotics
#:b. Design
#:c. Optimization
#:d. Measurements (correct)
# Which of the following algorithms suffers from local minima of the objective function
#:a. Genetic algorithm
#:b. Evolutionary algorithm
#:c. Gradient descent (correct)
#:d. All three of the above

=== Section 2 ===

==== Section title: Computational complexity, ANN ====

==== Topics covered in this section ====

* Turing machines, computational complexity
* NP-hardness
* Reductions
* Learning Classifier Systems
* Co-evolutionary Algorithms
* Fitness Landscape Analysis
* Immunocomputing
* Swarms/Flocking
* Feedforward and Recurrent Networks, Backpropagation
* Spiking Neural Networks
* Self Organizing Maps
* Deep Learning

==== What forms of evaluation were used to test students’ performance in this section? ====

<div id="tab:OSSectionEval2">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|''' '''
! '''Yes/No'''
|-
| Development of individual parts of software product code
|align="center"| 1
|-
| Homework and group projects
|align="center"| 1
|-
| Midterm evaluation
|align="center"| 1
|-
| Testing (written or computer based)
|align="center"| 1
|-
| Reports
|align="center"| 0
|-
| Essays
|align="center"| 0
|-
| Oral polls
|align="center"| 0
|-
| Discussions
|align="center"| 1
|}

</div>

==== Typical questions for ongoing performance evaluation within this section ====

# What are Turing machines?
# What is computational complexity?
# What are artificial neural networks?
# What are Recurrent ANN?
# What is deep learning?

==== Typical questions for seminar classes (labs) within this section ====
# Give examples of algorithms of different computational complexities
# Give example of how one computes computational complexity
# What is a basic structure of an ANN?
# What is a fully connected ANN?
# Draw structure of LSTM RNN

==== Test questions for final assessment in this section ====

# Which of the following are neural networks architectures?
#:a. ANN, RNN, CNN
#:b. RNN, CNN, LSTM
#:c. RNN, CNN, fully connected (correct)
#:d. Reinforcement learning, Supervised learning
#Which types of machine learning can be used to learn policies for agents acting in dynamic environments, where marked datasets are not available?
#:a. Reinforcement learning, evolutionary algorithms (correct)
#:b. YOLO
#:c. Cauterization
#:d. Supervised learning
# What distinguishes deep learning?
#:a. The number of layers of the network, and the methods of gradient propagation aiming at lowering the effects of the vanishing gradients (correct)
#:b. Fully-connected layers
#:c. LSTM cells
#:d. Auto-encoding layers

=== Section 3 ===

==== Section title: Optimization, PSO ====

==== Topics covered in this section ====

* Ant Colony Optimization
* Ant Clustering Algorithm
* Particle Swarm Optimization
* Multiobjectiveness
* Foraging Algorithms
* Harmony Search
* Hebbian Learning, Boltzmann Machines

==== What forms of evaluation were used to test students’ performance in this section? ====

<div id="tab:OSSectionEval2">

{| style="border-spacing: 2px; border: 1px solid darkgray;"
|''' '''
! '''Yes/No'''
|-
| Development of individual parts of software product code
|align="center"| 1
|-
| Homework and group projects
|align="center"| 1
|-
| Midterm evaluation
|align="center"| 1
|-
| Testing (written or computer based)
|align="center"| 1
|-
| Reports
|align="center"| 0
|-
| Essays
|align="center"| 0
|-
| Oral polls
|align="center"| 0
|-
| Discussions
|align="center"| 1
|}

</div>

==== Typical questions for ongoing performance evaluation within this section ====

# What is a Foraging Algorithm
# What is PSO?
# What is a multi-objective optimization?
# What is Ant Colony Optimization?

==== Typical questions for seminar classes (labs) within this section ====
# Write PSO as a diagram
# Give example of a problem that can be solved using PSO
# Write a code implementing PSO for a problem with two variables
# How does the number of particles influence PSO performance?
# How do local minima influence PSO performance?

==== Test questions for final assessment in this section ====

# Which of the following can be used to solve optimization problems?
#:a. PSO, Genetic algorithm (correct)
#:b. CNN, PSO
#:c. CNN
#:d. RNN, PSO
# Which of the following can be used to find acceptable parameters of a process, given inequality constraints?
#:a. PSO, Genetic algorithm (correct)
#:b. CNN, PSO
#:c. CNN
#:d. RNN, PSO