Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Bio AI > Questions on Notes > Flashcards

Questions on Notes Flashcards

to become one with the knowledge

1
Q

Give details on the two brain initiatives

A

Brain Initiative:

  • broad looked into different ways of studying the brain
  • $300mil
  • finished

Human Brain Project:

  • map enough neurons to simulate part of the brain
  • $1bil
  • complained for being too narrow
  • ongoing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Name the types of output functions

A

Linear
Step
Sigmoid

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Describe the 4 learning rules

A

Plain Hebb: if both the pre-synaptic and post-synaptic neurons fired together the weights should increase.
Post-synaptic: if the post-synaptic neuron fires the weight should increase
Pre-synaptic: if the pre-synaptic neuron fires the weight should increase
Covariance: the increase in the weight is proportional to the difference between the two neurons

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Describe the types of neural networks

A

Perceptron:

  • single layer
  • linearly separable

Multilayer Perceptron:

  • not linearly separable as long as a non-linear output function is used
  • hidden layers

Recurrent Neural network

  • creates memory
  • used when there is a time series
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Describe the data sets needed and why

A

Training set
- this is used so the NN learns the weights

Validation set
- used to prevent overfitting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Give examples of applications for NN

A

NetTalk
- learnt to read aloud from written text

AlphaGo
- taught itself the game of Go

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are the limitations of NN

A
  • can be overfitted to the data
  • the results can be fooled
  • cyberattack of dataset
  • Bais from datasets used
  • Blackbox means it is not easily possible to understand the process the NN took
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Detail what is required to define a cellular system

A

Cell space
- 1D 2D 3D hexagonal

Neighbourhood
- which cells influence each other

Transition rule
- how a cell reacts to its neighbours

Boundary conditions
- Assigned, periodic, adiabatic, reflection

Initial conditions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the universality of CAs

A

Theoretically, they can compute anything as they are capable of universal computation. The game of life can do this

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Give examples for the uses of CAs

A
  • solve mazes

- model physics

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are the limitations of CAs

A
  • no way to predict the outcome without running it

- difficult to design the rules for a specific behaviour

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Detail the 4 pillars of evolution

A

Population: a group of several individuals
Diversity: individuals have different characteristics
Heredity: characteristics are transmitted over generations
Selection: individuals produce more offspring then the environment can support

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the genotype and phenotype

A

Genotype

  • the genetic material of the organism
  • selection does not directly operate

Phenotype

  • manifestation of the organism
  • selection operates on the phenotype
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Describe the differences between natural and artificial evolution

A
  • Fitness is a measure of the individual’s ability to solve the problem
  • Selection is according to the performance criteria
  • It is expected that the performance will improve over the generations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Describe the types of genetic representation

A

Discrete
- eg binary string mapping to several phenotypes

Sequence
- sequence of values (travelling salesman)

Real-value
- sequence of real values that represent parameters eg wing profile

Tree-based
- describes a tree with branching points and terminals

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Describe the types of fitness functions

A

Explicit: eg lift-drag
Implicit: maximum flight time
Subjective: most aesthetic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Why is selection pressure important

A

too strong and there is a rapid loss in diversity which could lead to a suboptimal solution.
too slow and the solution will not converge in a reasonable timeframe

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

List the types of selection

A

Proportional
Rank based
Tournament

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Describe proportional based selection

A
  • the probability of an individual producing offspring is proportional to its fitness with regards to the group’s fitness.
  • if fitness is uniform selection is weak
  • if there is an outperforming individual it can result in a lack of diversity
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Describe rank based selection

A
  • individuals are ranked based on their performance

- offspring is then produced proportional to their rank or from the selected best few

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Describe tournament based selection

A
  • a random group of set size is picked and competes against one another
  • the champion is then selected to produced offspring
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Describe the types of inheritance

A

One point: a proportion of the genotype at a point is switched
uniform: every other value in the genotype is switched
Arithmetic: an average of the genotype is produced

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

How can performance be monitored

A

Fitness landscape
- observe the average fitness of the population and the maximum fitness

Diversity
- when diversity decreases the potential for further evolution decreases

Only really useful when the problem is stationary

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Give examples of artificial evolution

A
  • To design an antenna
  • HyperNeat
  • Golem Project
  • RoboGen
25
Q

Describe HyperNeat

A

HyperNeat is used to evolve both the weights and the topology of a NN. This has then be used to design soft robots simulations designed for fast locomotion

26
Q

Describe the Golem Project

A
  • The fitness of a robot was tested in simulation

- The stick based robots where then 3D printed and tested in real life

27
Q

Describe RoboGen

A
  • Aimed to cross the reality gap, by ensuring the same performance in simulation and in real life
  • Described as having embodied cognition by designing the body and the controller at the same time
28
Q

Describe the thinking behind competitive co-evolution

A
  • may increase adaptivity by producing an evolutionary arms race
  • more complex solutions may arise
  • helps overcome the bootstrap problem (getting off the ground)
  • competitors have opposing fitness functions
  • to prevent the recycling of solutions a Hall of Fame can be created and then all the best individuals put against one another
29
Q

How would one ensure cooperation

A

homogenous swarm with swarm level selection

30
Q

List the differences in engineering and natural control

A

Engineering

  • designed system
  • limited DoF
  • simplified copy of biology
  • fully actuated
  • fully controlled
  • rigid body, model-based
  • central controller

Nature

  • systems are grown
  • high DoF
  • mostly soft
  • high redundancy
  • passive DoFs
  • distrubuted control
31
Q

What are CPG and describe their use

A
  • Biological neural circuits that produce rhythmic patterned outputs without sensory feedback or input.
  • They result in the smooth transition of gaits with simple 1D control
  • Globally stable non-linear oscillators are used for control and allow for self-stabilisation when perturbed
32
Q

Give a biological and engineering example where CPG are used

A
  • in the spine of vertebrate to control gait and gait changes
  • salamander robot
33
Q

Describe the process of traditional AI control and its key ideas

A

sensors -> perception -> modelling -> planning -> tast execution -> motor control -> actuators

every action requires a lot of processing, thinking, planning and model building

34
Q

Describe the process of behaviour based control and its key ideas

A

/ > | manipulate the world | > \
/ ^ \
/ > | build maps | > \
/ ^ \
sensors > | explore | > actuators
\ ^ /
\ > | avoid hitting things | > /
\ ^ /
\ > | locomote | > /

  • bottom-up hierarchical structure
  • reactive
  • layers easily added
35
Q

Describe the key ideas of behaviour based control

A

Embodiment: the physical body plays an important role in intelligence
Situatedness: control is based on its body and the environment
No planning: the world is it’s own best model
Emergent complexity: intelligence emerges rather than being programmed

36
Q

What is embodiment

A

The use of the physical design to reduce the computational workload taking inspiration from biological systems

37
Q

What is morphological computation

A

Using a high-dimensional, non-linear, compliant morphological structure the complex non-linear control is carried out by the structure. All that needs to be done is to identify the linear relationship between the structure and the desired outputs

38
Q

Give examples of morphological control

A
  • coffee balloon gripper
  • a swimming dead trout
  • slinky
39
Q

Detail the principles of swarm robotics

A
  • the swarm can solve complex problems that an individual could not solve
  • The swarm is composed of several individuals, some that may be lost or make mistakes but performance is not affected
  • Individuals have local sensory information, perform simple actions and have little/no memory
40
Q

Detail two types of swarm communication

A

Direct interaction

  • touch
  • wireless

Stigmergy
- communication through the environment eg pheromones

41
Q

What is a challenge of swarm intelligence

A

Difficult to find the rules for the individuals that result in the desired swarm behaviour

42
Q

List 5 process of swarm intelligence

A
  • Flocking (Reynolds flocking)
  • Pathfinding (Ant colony optimisation)
  • Optimisation (particle swarm optimisation)
  • Decision making
  • Clustering
43
Q

Describe Reynolds flocking

A
  1. Separation: Biods maintain a given distance from other biods
  2. Cohesion: Biod move towards the centre of mass of the neighbouring biods
  3. Alignment: Biods aline its angle with its neighbours
44
Q

Describe Ant colony optimisation

A
  1. As they move ants deposit a pheromone
  2. Pheromones decay with time
  3. Without pheromone, there is an equal probability of choosing both paths
  4. Ants follow the path with the highest pheromone concentration
  5. The short path has higher traffic as it takes less time to complete and therefore a higher pheromone concentration
  6. The short path will increasingly be chosen
45
Q

Describe Particle swarm optimisation

A
  1. Brave: keep moving in the same direction
  2. Conservative: move towards its own best previous position
  3. Swarm: move towards the best neighbour
46
Q

Describe decision making

A
  1. Individuals base their decisions on the opinion of their neighbour
  2. This is based on the quantity and the duration of the opinion of their neighbours
  3. The opinion is advertised for longer the more correct it is
47
Q

Describe clustering

A
  1. if an object is in an area of low density there is a high probability of it being picked up
  2. if the individual is in an area of high density there is a high probability of the object being deposited
48
Q

Give 1 real-life uses of swarms

A
  1. Flying robots to produce a dynamic communication

link

49
Q

Name the two types of reconfigurable robots and give an example for each

A

Chain: PolyBot
Lattice: A-TRON

50
Q

Describe morphogenesis

A

Morphogenesis produces structures without the need of a global map of the structure, instead of relying on self-organisation and emergent shapes.

  • morphogenes are stored on every robot. U activates itself and create V.
  • V inhibits V and U.
  • The reaction then diffuses through the swarm, creating patterns
51
Q

List design consideration of nanobots

A
  • size
  • shape
  • charge
  • cargo
  • material
52
Q

List the pros and cons of DNA memory

A

Pros
- Extremely high data density (10^3 times that of an optical disk)
Opertintiy for parallel computing
- Low power

Cons

  • Expensive
  • Error-prone
  • application specific and not easily rewritten
  • Not suitable for simple computation
  • Difficult to extract the data
53
Q

how can the travelling salesman problem be solved using DNA

A
  • Each location is given a name in DNA
  • Each path is given a name comprised of the end of the first location and the start of the end location.
  • This is then mixed in a test tube and every possible solution computed simultaneously
  • The stands are then ins[pected to find the short solution which contains all the locations
54
Q

Name and describe the method of computation using DNA

A

DNA Toehold system

- an ill-fitting strand is displaced by a strand of the correct length

55
Q

Describe DNA origami

A

Through the design of specific sequences, DNA can be made to fold in a meaningful way. Stables are used to guide how the structure folds

56
Q

Define the two types of creativity

A

Individualist “little c”
- creativity is a new mental combination that is expressed in the world

Sociocultural “big C”
- Creativity is the generation of a product that is judged to be novel and also appropriate, useful or valuable by a suitably knowledgable social group. novelty isn’t enough

57
Q

List the creative process

A
  1. Find the problem
  2. Acquire the knowledge
  3. gather related information
  4. incubation
  5. generate ideas
  6. combine ideas
  7. Select best ideas
  8. Externalise ideas
58
Q

Give an example of artificial creativity

A

GAN Picture

- Generated fake images which were then inputs into a discriminator which had been taught with a large training set

59
Q

Describe the challenges of artificial creativity

A
  • It is difficult to define what creativity is
  • Representing unknow unknows is difficult
  • Potentially, artificial creativity must be embodied

Bio AI (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions