/**
* The primary method in charge of learning. Adapts the permanence values of the synapses based on
* the input vector, and the chosen columns after inhibition round. Permanence values are
* increased for synapses connected to input bits that are turned on, and decreased for synapses
* connected to inputs bits that are turned off.
*
* @param c the {@link Connections} (spatial pooler memory)
* @param inputVector a integer array that comprises the input to the spatial pooler. There exists
* an entry in the array for every input bit.
* @param activeColumns an array containing the indices of the columns that survived inhibition.
*/
public void adaptSynapses(Connections c, int[] inputVector, int[] activeColumns) {
int[] inputIndices = ArrayUtils.where(inputVector, ArrayUtils.INT_GREATER_THAN_0);
double[] permChanges = new double[c.getNumInputs()];
Arrays.fill(permChanges, -1 * c.getSynPermInactiveDec());
ArrayUtils.setIndexesTo(permChanges, inputIndices, c.getSynPermActiveInc());
for (int i = 0; i < activeColumns.length; i++) {
Pool pool = c.getPotentialPools().get(activeColumns[i]);
double[] perm = pool.getDensePermanences(c);
int[] indexes = pool.getSparsePotential();
ArrayUtils.raiseValuesBy(permChanges, perm);
Column col = c.getColumn(activeColumns[i]);
updatePermanencesForColumn(c, perm, col, indexes, true);
}
}
@Test
public void testGetDensePotential() {
Connections connections = new Connections();
connections.setNumInputs(10);
Pool pool = new Pool(3);
Synapse[] synapses = new Synapse[3];
int[] connecteds = new int[] {0, 1, 0, 0, 1, 1, 0, 1, 0, 1};
for (int i = 0, j = 0; i < connecteds.length; i++) {
if (connecteds[i] == 0) continue;
synapses[j] = new Synapse(connections, null, null, pool, i, i);
synapses[j].setPermanence(
connections, 0.0); // 0.0 -> These aren't set as connected but simply members.
}
int[] expected = {0, 1, 0, 0, 1, 1, 0, 1, 0, 1};
int[] dense = pool.getDensePotential(connections);
assertTrue(Arrays.equals(expected, dense));
}
/**
* This method increases the permanence values of synapses of columns whose activity level has
* been too low. Such columns are identified by having an overlap duty cycle that drops too much
* below those of their peers. The permanence values for such columns are increased.
*
* @param c
*/
public void bumpUpWeakColumns(final Connections c) {
int[] weakColumns =
ArrayUtils.where(
c.getMemory().get1DIndexes(),
new Condition.Adapter<Integer>() {
@Override
public boolean eval(int i) {
return c.getOverlapDutyCycles()[i] < c.getMinOverlapDutyCycles()[i];
}
});
for (int i = 0; i < weakColumns.length; i++) {
Pool pool = c.getPotentialPools().get(weakColumns[i]);
double[] perm = pool.getSparsePermanences();
ArrayUtils.raiseValuesBy(c.getSynPermBelowStimulusInc(), perm);
int[] indexes = pool.getSparsePotential();
Column col = c.getColumn(weakColumns[i]);
updatePermanencesForColumnSparse(c, perm, col, indexes, true);
}
}
@Test
public void testGetDenseConnected() {
Connections connections = new Connections();
connections.setSynPermConnected(0.2d);
connections.setNumInputs(5);
Pool pool = new Pool(3);
Synapse[] synapses = new Synapse[3];
double[] perms = new double[] {0.0, 0.2, 0.0, 0.2, 0.2};
for (int i = 0, j = 0; i < perms.length; i++) {
if (perms[i] == 0) continue;
synapses[j] = new Synapse(connections, null, null, pool, i, i);
synapses[j++].setPermanence(connections, perms[i]);
}
int[] expected = {0, 1, 0, 1, 1};
int[] dense = pool.getDenseConnected(connections);
assertTrue(Arrays.equals(expected, dense));
int[] expected2 = {0, 1, 0, 1, 0}; // expect last bit below synPermConnected
synapses[2].setPermanence(connections, 0.19d); // set last bit below synPermConnected
dense = pool.getDenseConnected(connections);
assertTrue(Arrays.equals(expected2, dense));
}
