# Pre-Release Toolbox2 New Ideas

**URL:** https://discourse.flucoma.org/c/new-ideas/pre-release-toolbox2-new-ideas/14.md

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

---

## [About the Pre-Release Toolbox2 New Ideas category](https://discourse.flucoma.org/t/about-the-pre-release-toolbox2-new-ideas-category/382)

<div class="topic-metadata">

**Author:** [@tremblap](https://discourse.flucoma.org/u/tremblap)\
**Replies:** 0

</div>

This is a private group to discuss Pre-Public Releases of the Second Toolbox, since the forum will go public for Toolbox 1 mid-November. Place your new ideas here!

---

## [Biasing a query](https://discourse.flucoma.org/t/biasing-a-query/506)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 36\
**Last updated:** [July 27, 2022, 7:49pm UTC](https://discourse.flucoma.org/t/biasing-a-query/506 "2022-07-27T19:49:21Z")

</div>

So jumping on the discussion from the LPT thread and the concept from the hybrid synthesis thread I got to thinking about how to bias a query in the newschool ML context. For example, I want to create a multi-stage anal…

---

## [Regression + Classification = Regressification?](https://discourse.flucoma.org/t/regression-classification-regressification/547)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 63\
**Last updated:** [May 26, 2022, 4:20pm UTC](https://discourse.flucoma.org/t/regression-classification-regressification/547 "2022-05-26T16:20:45Z")

</div>

This is a potentially weird “thinking out loud” thing, but is there a way to have a regression for a classifier? More specifically, I’ll explain what I mean in a musical way. I have a corpus, which I can analyze however…

---

## [LTE - An alternative to LPT for people who don't care about "pitch"](https://discourse.flucoma.org/t/lte-an-alternative-to-lpt-for-people-who-dont-care-about-pitch/605)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 39\
**Last updated:** [May 14, 2021, 10:49am UTC](https://discourse.flucoma.org/t/lte-an-alternative-to-lpt-for-people-who-dont-care-about-pitch/605 "2021-05-14T10:49:36Z")

</div>

Initially posted this on Slack, but wanted to move the conversation (thinking out loud) over onto Discourse. Based on what @groma mentioned about the usefulness of higher coefficient count MFCCs to represent spectrum (a…

---

## [FluidDataSet .append](https://discourse.flucoma.org/t/fluiddataset-append/853)

<div class="topic-metadata">

**Author:** [@tedmoore](https://discourse.flucoma.org/u/tedmoore)\
**Replies:** 5\
**Last updated:** [April 5, 2021, 5:16pm UTC](https://discourse.flucoma.org/t/fluiddataset-append/853 "2021-04-05T17:16:43Z")

</div>

Greetings, I’ve found the FluidDataSet .merge and the FluidDataSetQuery .transformJoin, however I’m wondering if there is a .append. Something so that DataSet A: “a”: 0, 1 “b”, 2, 3 and DataSet B: “a”: 4, 5, 6 “b”:…

---

## [Giving fluid.dataset~ an index as well as a label](https://discourse.flucoma.org/t/giving-fluid-dataset-an-index-as-well-as-a-label/843)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 2\
**Last updated:** [March 22, 2021, 2:33pm UTC](https://discourse.flucoma.org/t/giving-fluid-dataset-an-index-as-well-as-a-label/843 "2021-03-22T14:33:32Z")

</div>

So I’ve been trying to build test corpora with the -comparison example and on top of other issues I’ve run in to I’m now having a thing where I can’t use my polybuffer~-based workflow since all the labels in the dataset …

---

## [Analysis "Pipeline"](https://discourse.flucoma.org/t/analysis-pipeline/828)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 9\
**Last updated:** [March 13, 2021, 3:56pm UTC](https://discourse.flucoma.org/t/analysis-pipeline/828 "2021-03-13T15:56:10Z")

</div>

Some else that came up during this week’s geek out is the idea of some kind of scriptable, or embed-able “analysis pipeline” , where you have a sequence of analyses/stats/scalings → dataset processes/reductions which ca…

---

## [More AI thinking](https://discourse.flucoma.org/t/more-ai-thinking/816)

<div class="topic-metadata">

**Author:** [@tremblap](https://discourse.flucoma.org/u/tremblap)\
**Replies:** 0\
**Last updated:** [March 8, 2021, 3:14pm UTC](https://discourse.flucoma.org/t/more-ai-thinking/816 "2021-03-08T15:14:56Z")

</div>

This is hillarious. I love the iPod example :slight\_smile: So don’t despair when you model is confused. you’re not alone :slight\_smile:

---

## [A fluid.datasetstats~ object](https://discourse.flucoma.org/t/a-fluid-datasetstats-object/804)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 3\
**Last updated:** [March 5, 2021, 12:22pm UTC](https://discourse.flucoma.org/t/a-fluid-datasetstats-object/804 "2021-03-05T12:22:24Z")

</div>

In playing around with some of the IQR stuff (as well as encountering some bugs) it occurred to me that it would be super useful (sometimes) be be able to see the stats for columns inside of a dataset. This can be useful…

---

## [Quantitative Trading](https://discourse.flucoma.org/t/quantitative-trading/640)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 2\
**Last updated:** [August 31, 2020, 11:57am UTC](https://discourse.flucoma.org/t/quantitative-trading/640 "2020-08-31T11:57:26Z")

</div>

So I had a Skype chat with a friend of @Angela’s today (well, friend of mine too now) who was a fairly successful (fancy-pants MIT-trained) quantitative trader, who has since retired from the bloodsucking world that that…

---

## [CLI for select objects from TB2](https://discourse.flucoma.org/t/cli-for-select-objects-from-tb2/632)

<div class="topic-metadata">

**Author:** [@jamesbradbury](https://discourse.flucoma.org/u/jamesbradbury)\
**Replies:** 3\
**Last updated:** [August 8, 2020, 9:04am UTC](https://discourse.flucoma.org/t/cli-for-select-objects-from-tb2/632 "2020-08-08T09:04:43Z")

</div>

What is the possibility of having some of the algos from TB2 made available via CLI? I’d like to port them into REAPER to get a bit more hands on with using them in a sound design capacity. Taking a look at the wrapper n…

---

## [Access to the underlying fluid synths in SC](https://discourse.flucoma.org/t/access-to-the-underlying-fluid-synths-in-sc/626)

<div class="topic-metadata">

**Author:** [@spluta](https://discourse.flucoma.org/u/spluta)\
**Replies:** 2\
**Last updated:** [August 5, 2020, 9:57am UTC](https://discourse.flucoma.org/t/access-to-the-underlying-fluid-synths-in-sc/626 "2020-08-05T09:57:02Z")

</div>

I would like to have access to the synths that the Fluid objects create on the server, or at least be able to send them messages. I would especially like to be able to pause and unpause them so they are not taking up CPU…

---

## [FluidDataSet.renamePoint](https://discourse.flucoma.org/t/fluiddataset-renamepoint/621)

<div class="topic-metadata">

**Author:** [@spluta](https://discourse.flucoma.org/u/spluta)\
**Replies:** 7\
**Last updated:** [August 3, 2020, 4:59pm UTC](https://discourse.flucoma.org/t/fluiddataset-renamepoint/621 "2020-08-03T16:59:56Z")

</div>

This is killing me. Let’s say I have a DS with 10 data points, numbered in order. Then I remove dataPoint 6. Now I have points labeled 0, 1, 2, 3, 4, 5, 7, 8, 9. How do I make it so there is no gap with the current tools…

---

## [Descriptor dimensionality reduction](https://discourse.flucoma.org/t/descriptor-dimensionality-reduction/606)

<div class="topic-metadata">

**Author:** [@b.hackbarth](https://discourse.flucoma.org/u/b.hackbarth)\
**Replies:** 22\
**Last updated:** [August 2, 2020, 11:55am UTC](https://discourse.flucoma.org/t/descriptor-dimensionality-reduction/606 "2020-08-02T11:55:10Z")

</div>

Hi all, I’m thinking about working on some descriptor dimensionality reduction for audioguide to create something like a 2D space for timbre. Anyone care to share any tips/algorithms/methods that work well? @jamesbradbu…

---

## [Vowel recognition](https://discourse.flucoma.org/t/vowel-recognition/613)

<div class="topic-metadata">

**Author:** [@danieleghisi](https://discourse.flucoma.org/u/danieleghisi)\
**Replies:** 10\
**Last updated:** [July 27, 2020, 1:10pm UTC](https://discourse.flucoma.org/t/vowel-recognition/613 "2020-07-27T13:10:28Z")

</div>

Hello everyone, weird question about vowel recognition. I know of course of formants and I think I have a basic understanding of the main current methods to get them, but I do not have any understanding of a more fundam…

---

## [Create FluidDataSet on NRT server](https://discourse.flucoma.org/t/create-fluiddataset-on-nrt-server/576)

<div class="topic-metadata">

**Author:** [@tedmoore](https://discourse.flucoma.org/u/tedmoore)\
**Replies:** 5\
**Last updated:** [July 17, 2020, 11:06pm UTC](https://discourse.flucoma.org/t/create-fluiddataset-on-nrt-server/576 "2020-07-17T23:06:11Z")

</div>

Greetings, Is there a way I can create a FluidDataSet on a NRT server in SuperCollider (via an osc message used in a Score)? What could that osc message be? Also, can I write it to a json that way also? Thanks! T

---

## [Transformpoint for fluid.mds~](https://discourse.flucoma.org/t/transformpoint-for-fluid-mds/575)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 10\
**Last updated:** [July 16, 2020, 3:57pm UTC](https://discourse.flucoma.org/t/transformpoint-for-fluid-mds/575 "2020-07-16T15:57:36Z")

</div>

Don’t know if this falls into the same category as the read/write messages being missing, but fluid.mds~ doesn’t seem to have a transformpoint message/option. This would be super useful, for fitting a pre-computed reduc…

---

## [Dimensionality reduction (mixing the rational and irrational)](https://discourse.flucoma.org/t/dimensionality-reduction-mixing-the-rational-and-irrational/534)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 22\
**Last updated:** [July 13, 2020, 12:23pm UTC](https://discourse.flucoma.org/t/dimensionality-reduction-mixing-the-rational-and-irrational/534 "2020-07-13T12:23:34Z")

</div>

As part of my attempt to move some of what I’ve been doing into ML land (and after having a fruitful geek out with @jamesbradbury) I wanted to try to use dimensionality reduction in a way that still “made sense”. That i…

---

## [FluidBufCompose.kr - why not?](https://discourse.flucoma.org/t/fluidbufcompose-kr-why-not/519)

<div class="topic-metadata">

**Author:** [@spluta](https://discourse.flucoma.org/u/spluta)\
**Replies:** 9\
**Last updated:** [July 3, 2020, 9:55pm UTC](https://discourse.flucoma.org/t/fluidbufcompose-kr-why-not/519 "2020-07-03T21:55:57Z")

</div>

I don’t know if it isn’t there because you don’t want it or because it isn’t ready yet, but I am really jonesing for FluidBufCompose.kr right now. From the example: ~extractor = FluidProcessSlices({|src,start,num,data| …

---

## [(more) ways to get data in and out of fluid.dataset~](https://discourse.flucoma.org/t/more-ways-to-get-data-in-and-out-of-fluid-dataset/539)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 6\
**Last updated:** [July 1, 2020, 10:19pm UTC](https://discourse.flucoma.org/t/more-ways-to-get-data-in-and-out-of-fluid-dataset/539 "2020-07-01T22:19:42Z")

</div>

Now that I’m playing more with the TB2 bits I’m wondering about how to best approach certain things. As I figured out in this thread, creating a subset of a fluid.dataset~ with fluid.datasetquery~ (specifically as a way…

---

## [Onset-based regression (JIT-MFCC example)](https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 49\
**Last updated:** [June 29, 2020, 9:17am UTC](https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464 "2020-06-29T09:17:26Z")

</div>

One of the things I was trying to do very early on was to somewhat emulation the behavior of the Sensory Percussion software where you can train a handful of sounds, then play back arbitrary material and it would return …

---

## [@startframe/@numframes attributes for fluild.bufnmfcross~](https://discourse.flucoma.org/t/startframe-numframes-attributes-for-fluild-bufnmfcross/526)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 0\
**Last updated:** [June 21, 2020, 5:21pm UTC](https://discourse.flucoma.org/t/startframe-numframes-attributes-for-fluild-bufnmfcross/526 "2020-06-21T17:21:22Z")

</div>

From what @tremblap said at the last FluCoMaChaT, fluild.bufnmfcross~ has changed a bunch already from what we “accidentally” got in alpha03, so this may already be the case, but it would be great to be able to specify @…

---

## [Various experiments with the LPT patch](https://discourse.flucoma.org/t/various-experiments-with-the-lpt-patch/501)

<div class="topic-metadata">

**Author:** [@tremblap](https://discourse.flucoma.org/u/tremblap)\
**Replies:** 18\
**Last updated:** [June 1, 2020, 1:34pm UTC](https://discourse.flucoma.org/t/various-experiments-with-the-lpt-patch/501 "2020-06-01T13:34:54Z")

</div>

Dear all Here is a list of potential ideas on how to play with the LPT example provided and discussed about in yesterday’s presentation. It was not recorded and maybe some of them did not come across clearly, so this is…

---

## [The ability to double-click fluid.dataset~](https://discourse.flucoma.org/t/the-ability-to-double-click-fluid-dataset/504)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 0\
**Last updated:** [May 31, 2020, 12:45pm UTC](https://discourse.flucoma.org/t/the-ability-to-double-click-fluid-dataset/504 "2020-05-31T12:45:35Z")

</div>

It would be great to be able to double-click fluid.datatset~ in the same way you can with dict or coll .

---

## [Newschool vs oldschool syntax (transform \<dataset\> \<dataset\>)](https://discourse.flucoma.org/t/newschool-vs-oldschool-syntax-transform-dataset-dataset/495)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 4\
**Last updated:** [May 26, 2020, 2:55pm UTC](https://discourse.flucoma.org/t/newschool-vs-oldschool-syntax-transform-dataset-dataset/495 "2020-05-26T14:55:03Z")

</div>

Not really a suitable category for the TB2 stuff, so I popped it in here as it seems the most suitable. One thing that occurred to me while looking through (all the exciting) new additions is that the syntax being used …

---

## [Dimensionality reduction, disparate spaces, and speed](https://discourse.flucoma.org/t/dimensionality-reduction-disparate-spaces-and-speed/488)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 4\
**Last updated:** [May 17, 2020, 9:02am UTC](https://discourse.flucoma.org/t/dimensionality-reduction-disparate-spaces-and-speed/488 "2020-05-17T09:02:02Z")

</div>

So in light of new bits coming out soon, I’ve been thinking about how I might apply dimensionality reduction. I’m sure a bunch more will become clear once we have the new tools, and @tremblap mentioned doing a video wal…

---

## [Fluid.kdtree~ as entrymatcher~ replacement(ish)](https://discourse.flucoma.org/t/fluid-kdtree-as-entrymatcher-replacement-ish/468)

<div class="topic-metadata">

**Author:** [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Replies:** 3\
**Last updated:** [May 1, 2020, 10:01am UTC](https://discourse.flucoma.org/t/fluid-kdtree-as-entrymatcher-replacement-ish/468 "2020-05-01T10:01:34Z")

</div>

So after getting something kind of useful out of fluid.knn~ in the other thread (I’m going to do some more testing tomorrow and see how I get on with some additional stuff @tremblap mentioned offline) I wanted to see wha…

---

## [NNSize question](https://discourse.flucoma.org/t/nnsize-question/450)

<div class="topic-metadata">

**Author:** [@spluta](https://discourse.flucoma.org/u/spluta)\
**Replies:** 26\
**Last updated:** [April 2, 2020, 6:56pm UTC](https://discourse.flucoma.org/t/nnsize-question/450 "2020-04-02T18:56:02Z")

</div>

So, I am really just checking my math here. If I have a 16 dimensional space, where each dimension has 100 points, then my space would have 100^16 points or 10^32? Then, if I train a Neural Net to traverse this space, …

---

## [Frightening link - I hope you \[...\]](https://discourse.flucoma.org/t/frightening-link-i-hope-you/441)

<div class="topic-metadata">

**Author:** [@tremblap](https://discourse.flucoma.org/u/tremblap)\
**Replies:** 4\
**Last updated:** [March 9, 2020, 10:53am UTC](https://discourse.flucoma.org/t/frightening-link-i-hope-you/441 "2020-03-09T10:53:16Z")

</div>

… enjoy? … dream about how we can do this on sounds? … are slightly afraid? https://thispersondoesnotexist.com/

---

## [SC: FluidDataSet and FluidLabelSet "get" method like Buffer "getn"](https://discourse.flucoma.org/t/sc-fluiddataset-and-fluidlabelset-get-method-like-buffer-getn/387)

<div class="topic-metadata">

**Author:** [@tedmoore](https://discourse.flucoma.org/u/tedmoore)\
**Replies:** 1\
**Last updated:** [January 4, 2020, 12:44pm UTC](https://discourse.flucoma.org/t/sc-fluiddataset-and-fluidlabelset-get-method-like-buffer-getn/387 "2020-01-04T12:44:21Z")

</div>

Hello, I’ve noticed that when using “getPoint” or “getLabel” in some sort of loop (in order to get multiple responses) I need to insert an “s.sync” in order to get an accurate response. I have also since noticed it in t…

[Next page](https://discourse.flucoma.org/c/new-ideas/pre-release-toolbox2-new-ideas/14.md?page=1)
