A column beginning to temporally pool a pattern can "throw off"a higher layer.

[calumroy]

When a column in a layer tries to temporally pool this means the output is disrupted because the column stays active longer then it normally would (this isn't a problem but it means the next columns that normally would be activated are eventually not activated at all and skipped). The output sequence from this layer to a higher layer changes because of this. This means columns in the higher layer will burst because they were not expecting a change of sequence.

The bursting every time a lower column tries to temporally pool makes forming higher level stable temporal patterns take longer then it should have. A solution needs to be found were when a column temporally pools the higher layer don't burst because of this.

[calumroy]

A solution may be to somehow have temporal pooling occur faster in higher layers. This would cause higher layers to learn to temporally pool patterns before lower layers could. The reason this helps is that the higher layer would then not be surprised and burst when a lower layer then learns to temporal pool part of a sequence. Since the higher layer has temporally pooled over the lower layers output sequence first when the lower layer then skips part of it's output due to it learning to temporally pool the higher layer doesn't burst as it's output stays constant regardless.