# HTM.Java

**URL:** https://discourse.numenta.org/c/engineering/htm-java/27.md?page=1

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

**Page:** 2

---

## [Converting NuPIC params to HTM.Java params](https://discourse.numenta.org/t/converting-nupic-params-to-htm-java-params/4588)

<div class="topic-metadata">

**Author:** [@Matheus\_Araujo](https://discourse.numenta.org/u/Matheus_Araujo)\
**Replies:** 3\
**Last updated:** [September 20, 2018, 11:02am UTC](https://discourse.numenta.org/t/converting-nupic-params-to-htm-java-params/4588 "2018-09-20T11:02:29Z")

</div>

Dear all, I’m trying to implement an anomaly detection that takes a timed series file as input as in HotGym project but its values are coordinates\[latitude, longitude, radius\] just like the mine-hack project. For the ti…

---

## [Passing Model Params generated by Swarming to HTM.java](https://discourse.numenta.org/t/passing-model-params-generated-by-swarming-to-htm-java/2616)

<div class="topic-metadata">

**Author:** [@wip\_user](https://discourse.numenta.org/u/wip_user)\
**Replies:** 3\
**Last updated:** [September 19, 2018, 4:11pm UTC](https://discourse.numenta.org/t/passing-model-params-generated-by-swarming-to-htm-java/2616 "2018-09-19T16:11:04Z")

</div>

Hi @cogmission Is there a way to pass Model parameters generated by Swarming to HTM.java ? MH

---

## [Question about supporting multi variable anomaly detection](https://discourse.numenta.org/t/question-about-supporting-multi-variable-anomaly-detection/2655)

<div class="topic-metadata">

**Author:** [@z-wony](https://discourse.numenta.org/u/z-wony)\
**Replies:** 1\
**Last updated:** [September 19, 2018, 4:05pm UTC](https://discourse.numenta.org/t/question-about-supporting-multi-variable-anomaly-detection/2655 "2018-09-19T16:05:49Z")

</div>

Hi HTM experts. I’m a novice about HTM, this is first time, and I’ve been tested htm.java-example. I’ve been used HTM studio, and I feel it’s great. But it could analysis just single variable from my csv file. I wond…

---

## [Anomaly detection for a square wave that stops](https://discourse.numenta.org/t/anomaly-detection-for-a-square-wave-that-stops/4262)

<div class="topic-metadata">

**Author:** [@longtimer](https://discourse.numenta.org/u/longtimer)\
**Replies:** 1\
**Last updated:** [August 15, 2018, 2:49pm UTC](https://discourse.numenta.org/t/anomaly-detection-for-a-square-wave-that-stops/4262 "2018-08-15T14:49:29Z")

</div>

Hello, I am playing with anomaly detection using a network with a Spatial Pooler and Temporal Memory on an example of a slightly noisy square wave that just stops at a point in time. I am wondering if like an SVM I shou…

---

## [Using HTM with Kryo serializer](https://discourse.numenta.org/t/using-htm-with-kryo-serializer/3532)

<div class="topic-metadata">

**Author:** [@alexsch](https://discourse.numenta.org/u/alexsch)\
**Replies:** 1\
**Last updated:** [March 2, 2018, 5:26pm UTC](https://discourse.numenta.org/t/using-htm-with-kryo-serializer/3532 "2018-03-02T17:26:51Z")

</div>

Hello, My question just arises from the topic NPE during org.numenta.nupic.network.Layer deserialization I need to serialize HTM classes using Kryo serializer which used in Spark Streaming application. The serializati…

---

## [NPE during org.numenta.nupic.network.Layer deserialization](https://discourse.numenta.org/t/npe-during-org-numenta-nupic-network-layer-deserialization/3506)

<div class="topic-metadata">

**Author:** [@alexsch](https://discourse.numenta.org/u/alexsch)\
**Replies:** 3\
**Last updated:** [February 27, 2018, 12:07pm UTC](https://discourse.numenta.org/t/npe-during-org-numenta-nupic-network-layer-deserialization/3506 "2018-02-27T12:07:01Z")

</div>

Hello, There is one more problem with the HTM deserializaton. We use the SerializerCore to serialize/deserialize HTM classes. SerializerCore htmSerializer = new SerializerCore(SerialConfig.DEFAULT\_REGISTERED\_TYPES); D…

---

## [SDRClassifier serialization](https://discourse.numenta.org/t/sdrclassifier-serialization/3505)

<div class="topic-metadata">

**Author:** [@alexsch](https://discourse.numenta.org/u/alexsch)\
**Replies:** 5\
**Last updated:** [February 26, 2018, 10:02am UTC](https://discourse.numenta.org/t/sdrclassifier-serialization/3505 "2018-02-26T10:02:40Z")

</div>

Hello, We are using the HTM to detect anomalies in our Spark Streaming process. After running our project the following exception arises during the deserialization: java.io.InvalidClassException: no.uib.cipr.matrix.sp…

---

## [Classification and Predict value of Output class](https://discourse.numenta.org/t/classification-and-predict-value-of-output-class/3147)

<div class="topic-metadata">

**Author:** [@Usama\_Furqan](https://discourse.numenta.org/u/Usama_Furqan)\
**Replies:** 7\
**Last updated:** [December 13, 2017, 9:54pm UTC](https://discourse.numenta.org/t/classification-and-predict-value-of-output-class/3147 "2017-12-13T21:54:30Z")

</div>

Hi All, I have studied the HTM theory and currently playing with HTM implementation in java. I have checked few tests in PersistenceAPITest, they are related to anomaly detection. I have searched on forum about classica…

---

## [Help debugging the accuracy of anomaly detection on NYC\_taxi data](https://discourse.numenta.org/t/help-debugging-the-accuracy-of-anomaly-detection-on-nyc-taxi-data/3121)

<div class="topic-metadata">

**Author:** [@Kan](https://discourse.numenta.org/u/Kan)\
**Replies:** 1\
**Last updated:** [November 30, 2017, 12:26pm UTC](https://discourse.numenta.org/t/help-debugging-the-accuracy-of-anomaly-detection-on-nyc-taxi-data/3121 "2017-11-30T12:26:21Z")

</div>

Hi, This is my first time to play around with the HTM.java. I tried it with nyc\_taxi.csv data in NAB. But I got inaccurate results. An abstract of the results record\_num :10051 raw\_value :15926.0 prediction :17002.6…

---

## [Feedback on network setup for anomaly detection](https://discourse.numenta.org/t/feedback-on-network-setup-for-anomaly-detection/2778)

<div class="topic-metadata">

**Author:** [@Andrea\_Giordano](https://discourse.numenta.org/u/Andrea_Giordano)\
**Replies:** 12\
**Last updated:** [September 9, 2017, 11:19am UTC](https://discourse.numenta.org/t/feedback-on-network-setup-for-anomaly-detection/2778 "2017-09-09T11:19:21Z")

</div>

Hi, I’m looking for tuning my network to perform anomaly detection. I’d like to have a feedback on the parameters I set to understand if I made errors. An abstract of my dataset with computed anomaly score with the fo…

---

## [Anomaly detection stops after a number of output](https://discourse.numenta.org/t/anomaly-detection-stops-after-a-number-of-output/2785)

<div class="topic-metadata">

**Author:** [@Andrea\_Giordano](https://discourse.numenta.org/u/Andrea_Giordano)\
**Replies:** 7\
**Last updated:** [September 7, 2017, 5:54pm UTC](https://discourse.numenta.org/t/anomaly-detection-stops-after-a-number-of-output/2785 "2017-09-07T17:54:25Z")

</div>

Hi, I’m executing anomaly detection with HTM.Java. I noted that after it pulled out a number of scores (around 1.000) it stops and doesn’t calculate others. But my dataset is composed by 180.000 records… No errors are …

---

## [Performance optimization of HTM.java](https://discourse.numenta.org/t/performance-optimization-of-htm-java/2652)

<div class="topic-metadata">

**Author:** [@ibobak](https://discourse.numenta.org/u/ibobak)\
**Replies:** 15\
**Last updated:** [September 3, 2017, 11:21am UTC](https://discourse.numenta.org/t/performance-optimization-of-htm-java/2652 "2017-09-03T11:21:10Z")

</div>

We were estimating the ability of HTM.java to perform well in the condition when the data stream is very fast, but found out that in our case it was capable of processing just 100 records per second. For our real busine…

---

## [Htm anomaly values differs in two project](https://discourse.numenta.org/t/htm-anomaly-values-differs-in-two-project/2752)

<div class="topic-metadata">

**Author:** [@Andrea\_Giordano](https://discourse.numenta.org/u/Andrea_Giordano)\
**Replies:** 10\
**Last updated:** [September 2, 2017, 11:52am UTC](https://discourse.numenta.org/t/htm-anomaly-values-differs-in-two-project/2752 "2017-09-02T11:52:40Z")

</div>

Hi, I’m trying to integrate HTM in my FLINK instance. Initially I implemented HTM in a simple Java project, just to learn and to deal with my dataset and I obtained great results. Later I used Flink-HTM library from E…

---

## [Applying model params from swarm into Java](https://discourse.numenta.org/t/applying-model-params-from-swarm-into-java/2769)

<div class="topic-metadata">

**Author:** [@chiwai](https://discourse.numenta.org/u/chiwai)\
**Replies:** 1\
**Last updated:** [September 1, 2017, 4:04pm UTC](https://discourse.numenta.org/t/applying-model-params-from-swarm-into-java/2769 "2017-09-01T16:04:21Z")

</div>

Hello, I have got a problem. I took my time series csv file to Swarm in Nupic Python and got a model\_params,py which includes the parameters of model. Then I want to turn it into HTM.java code. I have set some of them t…

---

## [How to complement a completed CPU Utilization NAB using HTM.java?](https://discourse.numenta.org/t/how-to-complement-a-completed-cpu-utilization-nab-using-htm-java/2749)

<div class="topic-metadata">

**Author:** [@theseusyang](https://discourse.numenta.org/u/theseusyang)\
**Replies:** 4\
**Last updated:** [August 28, 2017, 1:30am UTC](https://discourse.numenta.org/t/how-to-complement-a-completed-cpu-utilization-nab-using-htm-java/2749 "2017-08-28T01:30:29Z")

</div>

I have downloaded NAB codes to run it. I find some features only in Nupic not in HTM.java, so If I want make an simple application using pure HTM.java, How to do it? including parameter setting? theseus yang

---

## [Gradle Build Failed](https://discourse.numenta.org/t/gradle-build-failed/2724)

<div class="topic-metadata">

**Author:** [@chiwai](https://discourse.numenta.org/u/chiwai)\
**Replies:** 7\
**Last updated:** [August 25, 2017, 10:47am UTC](https://discourse.numenta.org/t/gradle-build-failed/2724 "2017-08-25T10:47:19Z")

</div>

Is it normal? \[image\] I built it with jdk1.8.0\_131 and jre1.8.0\_141 on Windows 10 following this post https://github.com/numenta/htm.java/wiki/Eclipse-Setup-Tips

---

## [Flink Anomaly Detection](https://discourse.numenta.org/t/flink-anomaly-detection/2577)

<div class="topic-metadata">

**Author:** [@harshith99](https://discourse.numenta.org/u/harshith99)\
**Replies:** 1\
**Last updated:** [July 24, 2017, 7:03am UTC](https://discourse.numenta.org/t/flink-anomaly-detection/2577 "2017-07-24T07:03:47Z")

</div>

Hi, I am relatively to new to HTM.java. we are working on a project where we need to monitor the server logs in real time. We are using Apache Flink for streaming. If there is any sudden spike in the number of transacti…

---

## [Random Distributed Scalar Encoder :High Memory & CPU Usage](https://discourse.numenta.org/t/random-distributed-scalar-encoder-high-memory-cpu-usage/2571)

<div class="topic-metadata">

**Author:** [@wip\_user](https://discourse.numenta.org/u/wip_user)\
**Replies:** 0\
**Last updated:** [July 23, 2017, 1:39am UTC](https://discourse.numenta.org/t/random-distributed-scalar-encoder-high-memory-cpu-usage/2571 "2017-07-23T01:39:50Z")

</div>

Hi I have noticed Random Distributed Scalar Encoder using lot more memory and CPU compare to Scalar Encoder . reaching 100% cpu for one “Random Distributed Scalar Encoder” variable. Has anyone faced similar problem ? …

---

## [How to configure in HTM.java to identify weekly and daily patterns](https://discourse.numenta.org/t/how-to-configure-in-htm-java-to-identify-weekly-and-daily-patterns/2569)

<div class="topic-metadata">

**Author:** [@wip\_user](https://discourse.numenta.org/u/wip_user)\
**Replies:** 4\
**Last updated:** [July 21, 2017, 10:06pm UTC](https://discourse.numenta.org/t/how-to-configure-in-htm-java-to-identify-weekly-and-daily-patterns/2569 "2017-07-21T22:06:39Z")

</div>

Hi Pls let me know how to configure in HTM.java to identify weekly and daily patterns .

---

## [Anomaly Score Difference betewen HTM studio and HTM.java](https://discourse.numenta.org/t/anomaly-score-difference-betewen-htm-studio-and-htm-java/2559)

<div class="topic-metadata">

**Author:** [@wip\_user](https://discourse.numenta.org/u/wip_user)\
**Replies:** 5\
**Last updated:** [July 20, 2017, 8:57pm UTC](https://discourse.numenta.org/t/anomaly-score-difference-betewen-htm-studio-and-htm-java/2559 "2017-07-20T20:57:16Z")

</div>

Hi I ran rec-center-hourly.csv file through HTM studio and HTM.java ,I got different anomaly scores , what could be the reason ? pls see attached picture of anomaly score \[image\] I have used NetworkAPIDemo.java in h…

---

## [Memory footprint of Network object \[HTM.java\]](https://discourse.numenta.org/t/memory-footprint-of-network-object-htm-java/2512)

<div class="topic-metadata">

**Author:** [@wip\_user](https://discourse.numenta.org/u/wip_user)\
**Replies:** 6\
**Last updated:** [July 11, 2017, 4:13am UTC](https://discourse.numenta.org/t/memory-footprint-of-network-object-htm-java/2512 "2017-07-11T04:13:20Z")

</div>

Hi Has anyone done performance testing on HTM.java ? Here are my observations Basic Network object is taking 21.3 mb of disk space during serialization and reached to 28mb after 44 records . Lot of times I got …

---

## [About integration of Flink-HTM](https://discourse.numenta.org/t/about-integration-of-flink-htm/2437)

<div class="topic-metadata">

**Author:** [@Andrea\_Giordano](https://discourse.numenta.org/u/Andrea_Giordano)\
**Replies:** 5\
**Last updated:** [June 20, 2017, 8:15pm UTC](https://discourse.numenta.org/t/about-integration-of-flink-htm/2437 "2017-06-20T20:15:29Z")

</div>

Hello! Honestly I didn't know where post these questions so I put here because I'm using java. Please move it if there is a better category. I prefer to post a pastebin pic in order to explain my problem because I wrote …

---

## [Missing anomaly scores](https://discourse.numenta.org/t/missing-anomaly-scores/2386)

<div class="topic-metadata">

**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Replies:** 6\
**Last updated:** [June 5, 2017, 11:19pm UTC](https://discourse.numenta.org/t/missing-anomaly-scores/2386 "2017-06-05T23:19:18Z")

</div>

Does that mean there are no anomaly score values coming out of HTM.Java? Or that they are all 0.0? Or are you referring to the likelihood calculation you’re doing outside of HTM.Java?

---

## [Parameter Optimization and identification](https://discourse.numenta.org/t/parameter-optimization-and-identification/2365)

<div class="topic-metadata">

**Author:** [@Usama\_Furqan](https://discourse.numenta.org/u/Usama_Furqan)\
**Replies:** 5\
**Last updated:** [June 5, 2017, 11:13pm UTC](https://discourse.numenta.org/t/parameter-optimization-and-identification/2365 "2017-06-05T23:13:55Z")

</div>

Hi All, I am exploring HTM.java for solving the problems of anomaly detection and classification. I have read the theory of HTM and also done the anomaly detection example for getting raw anomaly score. I have seen in…

---

## [Problem building htm.java (osx)](https://discourse.numenta.org/t/problem-building-htm-java-osx/2377)

<div class="topic-metadata">

**Author:** [@Andrea\_Giordano](https://discourse.numenta.org/u/Andrea_Giordano)\
**Replies:** 11\
**Last updated:** [June 2, 2017, 6:36pm UTC](https://discourse.numenta.org/t/problem-building-htm-java-osx/2377 "2017-06-02T18:36:58Z")

</div>

Hi guys, I'm trying to use htm.java to perform simple application. I'd like to execute some examples but I can't complete building tutorial. Here: github htm.java I'm at "build the docker image" step but when I enter…

---

## [Translating python model\_params to Java](https://discourse.numenta.org/t/translating-python-model-params-to-java/2369)

<div class="topic-metadata">

**Author:** [@phil\_d\_cat](https://discourse.numenta.org/u/phil_d_cat)\
**Replies:** 4\
**Last updated:** [June 2, 2017, 6:28pm UTC](https://discourse.numenta.org/t/translating-python-model-params-to-java/2369 "2017-06-02T18:28:05Z")

</div>

I used python to swarm my data in hopes of improving anomaly detection. I have the model\_params.py file now but some fields don't seem to have an obvious Java analog. Should there be 1:1 python params: java params? …

---

## [Error on getting anomaly score on giving input](https://discourse.numenta.org/t/error-on-getting-anomaly-score-on-giving-input/2356)

<div class="topic-metadata">

**Author:** [@Usama\_Furqan](https://discourse.numenta.org/u/Usama_Furqan)\
**Replies:** 2\
**Last updated:** [May 26, 2017, 8:46pm UTC](https://discourse.numenta.org/t/error-on-getting-anomaly-score-on-giving-input/2356 "2017-05-26T20:46:03Z")

</div>

Hi All, I am following the example as written in NetworkSetupExample.java (https://gist.github.com/cogmission/26700c261f3ad70c719b110b2e6d04a7) , I want to get anomaly score for the file rec-center-hourly.csv (found in…

---

## [Creating a network for unsupervised categorization](https://discourse.numenta.org/t/creating-a-network-for-unsupervised-categorization/2335)

<div class="topic-metadata">

**Author:** [@Russ\_Brasser](https://discourse.numenta.org/u/Russ_Brasser)\
**Replies:** 6\
**Last updated:** [May 24, 2017, 1:52am UTC](https://discourse.numenta.org/t/creating-a-network-for-unsupervised-categorization/2335 "2017-05-24T01:52:49Z")

</div>

I am brand new to HTM. I have been reading all about it and watched all of the videos, as well as reading through the forums. I have a good conceptual grasp , but I am struggling with how to construct a network for my pr…

---

## [Ubuntu - Eclipse - NetworkAPIDemo - NoClassDefFoundError: no/uib/cipr/matrix/sparse/FlexCompRowMatrix](https://discourse.numenta.org/t/ubuntu-eclipse-networkapidemo-noclassdeffounderror-no-uib-cipr-matrix-sparse-flexcomprowmatrix/2339)

<div class="topic-metadata">

**Author:** [@szingerpeter](https://discourse.numenta.org/u/szingerpeter)\
**Replies:** 6\
**Last updated:** [May 23, 2017, 8:33pm UTC](https://discourse.numenta.org/t/ubuntu-eclipse-networkapidemo-noclassdeffounderror-no-uib-cipr-matrix-sparse-flexcomprowmatrix/2339 "2017-05-23T20:33:08Z")

</div>

Dear All, I am facing problems, while trying to run the NetworkAPIDemo example with reference to the htm.java-examples If I try to run the code, I get the error: SLF4J: Failed to load class "org.slf4j.impl.StaticLogg…

---

## [Epoch timestamp? PublisherSupplier.builder()](https://discourse.numenta.org/t/epoch-timestamp-publishersupplier-builder/2298)

<div class="topic-metadata">

**Author:** [@phil\_d\_cat](https://discourse.numenta.org/u/phil_d_cat)\
**Replies:** 3\
**Last updated:** [May 8, 2017, 7:48pm UTC](https://discourse.numenta.org/t/epoch-timestamp-publishersupplier-builder/2298 "2017-05-08T19:48:18Z")

</div>

My data is a series of records like so: stamp, (epoch time LONG) asn, (UNSIGNED INT) probeType, (UNSIGNED SHORT INT) responseCode, (UNSIGNED TINY INT (bool?)) result (SIGNED INT) Im hoping to eventually run predict…

[Previous page](https://discourse.numenta.org/c/engineering/htm-java/27.md)

[Next page](https://discourse.numenta.org/c/engineering/htm-java/27.md?page=2)