# \#opf

**URL:** https://discourse.numenta.org/tag/opf/33.md

[Latest](https://discourse.numenta.org/latest.md) · [Categories](https://discourse.numenta.org/categories.md) · [Tags](https://discourse.numenta.org/tags.md)

---

## [Will the deprecated OPF be replaced?](https://discourse.numenta.org/t/will-the-deprecated-opf-be-replaced/5978)

<div class="topic-metadata">

**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Replies:** 13\
**Last updated:** [July 11, 2019, 11:41am UTC](https://discourse.numenta.org/t/will-the-deprecated-opf-be-replaced/5978 "2019-07-11T11:41:31Z")

</div>

No we are not committed to the OPF at all. It is an outdated interface. I think there is a place for something like the OPF, but it should be re-thought from scratch for a particular domain problem.

---

## [OPF Code Review (29 Aug 2011)](https://discourse.numenta.org/t/opf-code-review-29-aug-2011/2161)

<div class="topic-metadata">

**Author:** [@scott](https://discourse.numenta.org/u/scott)\
**Replies:** 0\
**Last updated:** [April 7, 2017, 7:34pm UTC](https://discourse.numenta.org/t/opf-code-review-29-aug-2011/2161 "2017-04-07T19:34:21Z")

</div>

\###Warning: page contains outdated information We have retained this page for historical reasons. This page provides some guidance to code reviewers of the initial OPF implementation. Changes from the Initial Draft …

---

## [The OPF and InferenceTypes](https://discourse.numenta.org/t/the-opf-and-inferencetypes/1214)

<div class="topic-metadata">

**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Replies:** 4\
**Last updated:** [May 12, 2019, 10:52am UTC](https://discourse.numenta.org/t/the-opf-and-inferencetypes/1214 "2019-05-12T10:52:01Z")

</div>

It looks like they are defined in an enum in the code, but I don’t see any descriptions of each inference type. It would be helpful if we could come up with some descriptions of each inference type.

---

## [Stop learning in Online Prediction Framework](https://discourse.numenta.org/t/stop-learning-in-online-prediction-framework/2389)

<div class="topic-metadata">

**Author:** [@kaustabpal](https://discourse.numenta.org/u/kaustabpal)\
**Replies:** 5\
**Last updated:** [June 6, 2017, 11:59am UTC](https://discourse.numenta.org/t/stop-learning-in-online-prediction-framework/2389 "2017-06-06T11:59:53Z")

</div>

I have a sequence like 1,2,5,4 and this sequence keeps on repeating. I am using opf to predict the next value in the sequence but I want the HTM model to stop learning at some point. How do I achieve this in Nupic?

---

## [Inference Types](https://discourse.numenta.org/t/inference-types/2156)

<div class="topic-metadata">

**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Replies:** 0\
**Last updated:** [April 7, 2017, 5:34pm UTC](https://discourse.numenta.org/t/inference-types/2156 "2017-04-07T17:34:22Z")

</div>

Each model instance holds and InferenceType, which defines what "type" of predictions this model makes. In essence, and inferenceType indicates to the Model which set of inferenceElements should be produced. NuPIC OPF …

---

## [Predicting Multiple Output Values](https://discourse.numenta.org/t/predicting-multiple-output-values/2078)

<div class="topic-metadata">

**Author:** [@jon](https://discourse.numenta.org/u/jon)\
**Replies:** 9\
**Last updated:** [April 5, 2017, 10:47am UTC](https://discourse.numenta.org/t/predicting-multiple-output-values/2078 "2017-04-05T10:47:12Z")

</div>

Long time listener, first time caller :slight\_smile: I've been really excited about the NUPIC/Numenta project for some time, and I'm just recently getting to really sit down and start playing with the code. Really liking…

---

## [Anomality score / likehood after model load](https://discourse.numenta.org/t/anomality-score-likehood-after-model-load/2002)

<div class="topic-metadata">

**Author:** [@captador](https://discourse.numenta.org/u/captador)\
**Replies:** 3\
**Last updated:** [March 15, 2017, 6:45pm UTC](https://discourse.numenta.org/t/anomality-score-likehood-after-model-load/2002 "2017-03-15T18:45:05Z")

</div>

Hello, One question to the community about bit strange behaviour for my anomality detector. I use cron to kick model run on new batch of data instead of continious run. I noticed that likehood goes to 0.5 after first m…