CapoCaccia

Cognitive Neuromorphic Engineering Workshop

User Tools

Site Tools


cc18:relational-networks-for-goal-directed-sensory-motor-task:overview

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
cc18:relational-networks-for-goal-directed-sensory-motor-task:overview [2018/03/28 14:18]
89.206.64.7
cc18:relational-networks-for-goal-directed-sensory-motor-task:overview [2019/05/16 20:20] (current)
Line 40: Line 40:
 mapping (SAG) unit. As a core architecture,​ we will use a three-way relation network mapping (SAG) unit. As a core architecture,​ we will use a three-way relation network
 proposed by Peter Diehl [1] (see Fig 1 on the left). This unit consists of four recurrently connected proposed by Peter Diehl [1] (see Fig 1 on the left). This unit consists of four recurrently connected
-populations of neurons (nodes), three of which represent one-dimensional variables and the forth+populations of neurons (nodes), three of which represent one-dimensional variables and the fourth
 one encodes a relation between them (e.g. A + B - C = 0). A crucial step in translating the one encodes a relation between them (e.g. A + B - C = 0). A crucial step in translating the
 proposed architecture in [1] to our specified task (see below) is to change the input from a rate encoded proposed architecture in [1] to our specified task (see below) is to change the input from a rate encoded
Line 93: Line 93:
 Figure 1: LEFT PANEL: Adapted figure from [1] showing a scheme of a three-way relational Figure 1: LEFT PANEL: Adapted figure from [1] showing a scheme of a three-way relational
 network. Yellow circles represent populations of LIF-neurons,​ blue circles represent inputs (given network. Yellow circles represent populations of LIF-neurons,​ blue circles represent inputs (given
-two input the network infers the remaining one). Blue arrows depict direction of connections,​+two input the network infers the remaining one). Blue arrows depict ​the direction of connections,​
 emphasizing recurrent connectivity. For convenience of the "​hard-wired"​ hardware implementation,​ emphasizing recurrent connectivity. For convenience of the "​hard-wired"​ hardware implementation,​
 the size of the S, A and H populations will be reduced to 256 neurons. The size of the G population the size of the S, A and H populations will be reduced to 256 neurons. The size of the G population
 will be reduced to 30 neurons. RIGHT PANEL: An example of state-to-action mapping for three will be reduced to 30 neurons. RIGHT PANEL: An example of state-to-action mapping for three
-various goals: (a) following the stimulus (G1), (b) avoiding the stimulus (G2), (c) keeping a fixed+various goals: (i) following the stimulus (G1), (ii) avoiding the stimulus (ii), (c) keeping a fixed
 distance from the stimulus (G3) distance from the stimulus (G3)
  
cc18/relational-networks-for-goal-directed-sensory-motor-task/overview.txt ยท Last modified: 2019/05/16 20:20 (external edit)