# Unusual prediction behaviour in htm.js

**URL:** https://discourse.numenta.org/t/unusual-prediction-behaviour-in-htm-js/5980
**Category:** Engineering
**Created:** [May 9, 2019, 1:21pm UTC](https://discourse.numenta.org/t/unusual-prediction-behaviour-in-htm-js/5980 "2019-05-09T13:21:53Z")
**Posts on this page:** 1
**Showing post:** 10

<div class="post-metadata">

### Author: ![marty1885](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/marty1885/32/1891_2.png) [@marty1885](https://discourse.numenta.org/u/marty1885)
#### Post date: [May 10, 2019, 1:33am UTC](https://discourse.numenta.org/t/unusual-prediction-behaviour-in-htm-js/5980/10 "2019-05-10T01:33:30Z")

</div>

> [@jimmyw](#):
>
> I guess there must be something to mitigate this effect

You also have the option to use the connect-to-all method (Grow synapse from a predictive cell to all previously active cell, not just the selected active cell.). It forces TM to learn A-A-A instead of A-A’-A’’ unless the sequence itself suggest otherwise. It is not implemented in htm.js/NuPIC tho.

> [@Exploring the "Repeating Inputs" problem](https://discourse.numenta.org/t/exploring-the-repeating-inputs-problem/5498/2):
>
> @Paul_Lamb Does that mean that higher-order memory doesn’t work under your strategy? May you describe exactly how to reproduce the problem? I have built a similar application as yours in tiny-htm; after a tiny change in my TM code (which seems to be a general bug). TM seems to learn the sequence ABCD… and ABCBCD… no problem. (The slowdown in predicting in due to me pressing the keyboard slower, not the computers fault.) Edit: My TM learned this connection to predict the sequence AABB… (Gree…

---

_[View the full topic](https://discourse.numenta.org/t/unusual-prediction-behaviour-in-htm-js/5980)._