Can an ANN Use a SR-Latch to Store Fuzzy Floating Point Variables?

Click For Summary

Discussion Overview

The discussion revolves around the use of an artificial neural network (ANN) to store fuzzy floating point variables, specifically through the implementation of a Set Reset Latch (SR-latch) concept. Participants explore the mathematical validity of this approach and its potential applications, including distinguishing musical notes based on convergence areas within the ANN's output.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • One participant proposes using an ANN to store fuzzy floating point variables by translating the hardware SR-latch concept into a neural network framework.
  • The mathematical goal is to determine if input is consecutively low or high, with modifications to the activation function to create three convergence areas: -1, 0, and 1.
  • Another participant questions the clarity of the original post and requests a graphic for better understanding.
  • A participant expresses uncertainty about the mathematical validity of the proposed idea and seeks feedback on whether it is merely creative or holds merit.
  • A video demonstration is shared, illustrating the ANN's output in distinguishing musical notes based on convergence areas.
  • There is a humorous exchange regarding the profitability of the ANN, with one participant suggesting that its value depends on market demand for the solution it provides.
  • A later reply critiques the lack of a clear question in the discussion, suggesting that this has hindered productive responses.

Areas of Agreement / Disagreement

Participants do not reach a consensus on the mathematical validity of the proposed ANN approach. There are mixed responses regarding the clarity of the original inquiry and the overall direction of the discussion.

Contextual Notes

The discussion includes limitations in clarity and specificity of questions posed, which may affect the depth of responses. There are unresolved aspects regarding the mathematical formulation and practical implications of the ANN's design.

ADDA
Messages
67
Reaction score
2
I'm attempting to use a artificial neural network to store a fuzzy floating point variable. While writing the code, I became somewhat creative. I used the idea of an Set Reset Latch and statistically translated the hardware SR-latch into an artificial neural network. My mathematical goal is to determine if input is consecutively low or high. To achieve this, I've modified the neural network idea slightly. Since I did not have a way to calculate error (also a reason for thinking this up), I pointed the error vector down in terms of the difference of the second derivative and first derivative of the end layer's nodes, so that the network would converge on less and less change of nodes. Also I've modified this activation function:

1.0 / (1.0 + e^(-x))

to allow for three convergence areas: -1, 0, 1, as seen in the following output of kmPlot:

Screenshot_20170927_163157.png
 
Computer science news on Phys.org
Okay. It is a little hard to read. But. What is your question, I do not seem to see one?
Could you please post a graphic image which would help us older citizens read your output?
 
I guess, I was wondering if my idea is valid mathematically. Or is it just creative?

I'm unsure how to post media... other than how I have already. Would you like the equation and explanation, jim mcnamara?
 
I've made the following video to show output of my ANN:

The dot pairs represent notes on a guitar: open to the left, low E on the bottom. I start with an open D. The colors represent convergence areas: red (-1), green (0), blue (1). The top dot is one SRANN's output, corresponding to the input of a octave overtone; the bottom dot, an octave fifth overtone. There is an input multiplier in the lower right corner. Magnitude is represented by the alpha channel. A convergence of 0 (green) discards a bright note as being an overtone. The goal is to distinguish between, let's say D3 and D4, or E3 and E4, as played halfway through the video.
 
ADDA said:
Does this ANN make Benjamins?
That depends on if you are selling a solution to a problem someone is willing to pay for. There’s a rule-of-thumb that says if you aren't profitable after doing something for a year, it’s just a hobby.
 
stoomart said:
That depends on if you are selling a solution to a problem someone is willing to pay for. There’s a rule-of-thumb that says if you aren't profitable after doing something for a year, it’s just a hobby.

Literally, I was being cute. My original title was "Does this ANN make sense." Then pun'd on cents to bills to benjamins.
 
FWIW - Since I thought you we trying to make a joke I let it slide. Rather than locking the thread that was basically nonsense. When you expect an answer ask a clear question. You will notice your funny question got no useful answers. This thread is going nowhere. Closed. Please consider asking a clear question.
Thanks.
 
  • Like
Likes   Reactions: Evo

Similar threads

Conditional Digital Feedback; is it a good Idea? (Neural Networks)
  • · Replies 1 ·
Replies
1
Views
2K
MHB Convexivity issues in a new type of network - NLP
  • · Replies 1 ·
Replies
1
Views
3K
Graduate How Do Artificial Neural Networks Use Output Data to Approximate Functions?
  • · Replies 2 ·
Replies
2
Views
3K
Floating Point Notation Question
  • · Replies 5 ·
Replies
5
Views
6K