COMP9444 Neural Networks and Deep Learning
Term 3, 2020
Exercises 8: Hopfield Networks
-
- Compute the weight matrix for a Hopfield network with the two memory vectors
[1, –1, 1, –1, 1, 1] and
[1, 1, 1, –1, –1, –1] stored in it.
- Confirm that both these vectors are stable states of this network.
- Consider the following weight matrix W:
0.0
| –0.2
| 0.2
| –0.2
| –0.2
|
–0.2
| 0.0
| –0.2
| 0.2
| 0.2
|
0.2
| –0.2
| 0.0
| –0.2
| –0.2
|
–0.2
| 0.2
| –0.2
| 0.0
| 0.2
|
–0.2
| 0.2
| –0.2
| 0.2
| 0.0
|
- Starting in the state [1, 1, 1, 1, –1], compute the
state flow to the stable state using asynchronous updates.
- Starting in the (same) state [1, 1, 1, 1, –1], compute
the next state using synchronous updates.