Neural Networks: Unsupervised Learning

13 important questions on Neural Networks: Unsupervised Learning

What is the third principle of self-organisation?

Cooperation: Modifications in synaptic weights at the neural level and in neurons at the network level tend to cooperate with each other.

What is the fourth principle of self-organisation?

Structural information: The underlying order and structure that exists in an input signal represents redundant information which is acquired by a self-organising system in the form of knowledge.

What does the Generalised Hebbian Learning algorithm do?

The update rule of Hebbian Learning guarantees to find suitable principle components, where the weights should be set to small random values and the learning rate should be small. It only considers preceding neurons in the loop.
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What is the goal of self-organising maps?

It visualises high dimensional data in lower dimension. To transform an incoming signal pattern of arbitrary dimension into a one- or two-dimensional discrete map, and perform this translation adaptively in a topologically ordered fashion.

What are features of self-organising maps?

Neurons become selectively tuned. Neurons become ordered compared to each other:
  • Ordering represents coordinate systems for different input features.
  • Topographic map is created in which spatial locations of the neurons in the lattice are indicative of the intrinsic statistical features contained in the input patterns.
The human brain also shows similar forms of organisation. They are so-called computational maps. Every spot in the network has a function for a specific thing.

What are the three processes in which the self-organising maps are achieved?

  • Competition
  • Cooperation
  • Synaptic adaptation

What does the process competition for creating self-organising maps consist of?

The neuron with the highest activation value wins. Select the neuron with the highest.

What does the process cooperation for creating self-organising maps consist of?

Winning neuron determines the spatial location of a topological neighbourhood of excited neurons.
  • We want to stay close to neurobiological notions.
  • hj,i is the topological neighbourhood j entered on winning neuron i.
  • dj,i is the lateral distance.

What is the activation spread?

The lateral distance between neurons i and j, which is defined for one dimension (dj,i = |j-i|) and for two dimensions (dj,i = ||rj - ri||).
The topological neighbourhood can shrink over time:

What does the process synaptic adaptation for creating self-organising maps consist of?

Excited neurons increase their individual values for this input pattern by adjusting the synaptic weights.
The weights are moved into the direction of the input vector. Neurons close to each other tend to have similar synaptic weights. The learning rate eta can be made dynamic.

What does the algorithm for self-organising maps overall look like?

1. Initialisation. Choose random values for the initial weights.
2. Sampling. Draw a sample x from the input space with a certain probability. Vector x represents the activation pattern that is applied to the lattice. The dimension is equal to m.
3. Similarity Matching. Find the best-matching (winning) neuron i(x) at time step n by using the minimum-distance Euclidean criterion.
4. Updating. Adjust the synaptic weight vectors of all neurons by using the update formula.
5. Continuation. Continue with step 2 until no noticeable changes in the feature map are observed.

What are two phases of self-organising maps?

  • Self-organising or ordering phase: 1000 iterations, desirable values eta0 0.1 and T2 = 1000, sigma0 equal to the radius of the lattice and set T1 to 1000/log sigma0.
  • Convergence phase: iterations = 500 x number of neurons, set eta to 0.01, neighbourhood function should contain only the nearest neighbours of the neurons, eventually reducing to one or zero neighbours.

What is a contextual map?

For example where the animal names are clustered.

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo