DeepLTK (Deep Learning Toolkit for LabVIEW) Examples

This repository contains a collection of examples demonstrating how to use DeepLTK (Deep Learning Toolkit for LabVIEW) for solving various machine learning problems.

1. Simple_Examples

A set of basic examples.

	Name	Description	Blog
	1.1. Logistic Regression Single Output	Boolean AND: Model the Boolean AND logic function.	Link
	1.2. Logistic Regression Multi Output	8-bit adder: Model function with multiple logistic outputs.	Link
	1.3. Linear Regression	Celsius → Fahrenheit: Model linear conversion function: convert Celsius to Fahrenheit.	Link
	1.4. Non-Linear Regression Single Output	sin(x): Model non-linear function: predict sin(x) on a given x value.
	1.5. Non-Linear Regression Multi-Output	[sin(x), cos(x)]: Model multiple non-linear functions simultaneously: predict both sin(x) and cos(x) on a given x value.	Link

2. Waveform_Processing

A set of examples for waveforms (1-dimensional signal).

	Name	Description	Blog
	2.1. WF Signal Classification	Waveform Signal Classification: Classify time-domain waveforms into Sine, Sawtooth, Triangle, Square, and Noise categories.	Link
	2.2.1. WF Signal Regression	Waveform Signal Regression: Predict the frequency of periodic signals under different conditions.	Link
	2.2.2. WF Signal Regression Multi-Output	Multiple Output Waveform Signal Regression: Extend Waveform_Signal_Regression to predict frequency, amplitude, phase, and DC offset.	Link
	2.3. PTLF Classification	Power Transmission Line Fault Classification: Classify waveforms from power transmission lines to detect faults.	Link
	2.4. WF Anomaly Detection	Waveform Anomaly Detection: Detect anomalies in waveforms from power transmission lines.	Link

3. Image_Processing

A set of image processing examples.

	Name	Description	Blog
	3.1. Image Regression	Analog Meter Recognition: Predict Analog Meter values from given Analog Meter images.	Link
	3.2. Image Classification	Image Classification: Classify objects in images into predefined categories.
	3.3. Object Detection	Object Detection: Detect and locate multiple objects within an image, identifying their boundaries.
Coming Soon!	3.4. Semantic Segmentation	Semantic Segmentation: Label each pixel in an image with a corresponding class for image segmentation.
	3.5. Visual Anomaly Detection	Unsupervised Visual Anomaly Detection: Identify and localize anomalies in images by detecting instances that deviate from normal patterns, without the need for labeled data.	Link