Posts

Extreme Learning Machines

Image
Brief Introduction to Extreme Learning Machines (ELM) Extreme Learning Machines (ELMs) are a type of feedforward neural network known for fast training speed and good generalization performance. The contain 2 active layers. A fixed random layer with activation functions and an entirely linear read-out layer.  Here's a point-wise introduction: Type: Single-hidden layer feedforward neural networks (SLFNs). Key Idea: Input weights and biases in the hidden layer are randomly assigned and not updated during training. Training: The read-out layer weights are analytically determined using least squares (no iterative backpropagation).  Single shot least square. Advantage: Extremely fast training compared to traditional neural networks. Application Areas: Regression, classification, clustering, and feature learning tasks. Limitation: Performance depends on hidden layer size and random initialization. Current State of the Art (as of 2025) ELM Variants: ...

Java Machine Learning Collection

 Java Machine Learning Collection: An archive of machine learning code and general algorithms written in Java. Neural Networks Associative Memory Random Number Generators Random Projections Image Compression General Algorithms The Java source code is written in the style of the Numerical Recipies books.  Short and simple, for the most part. Java Collection >>>>> Download

The Walsh Hadamard Transform

Image
The Walsh Hadamard Transform 

Neon Bulb Oscillators

Image
Neon Tube Oscillators  Fig. 1 High voltage to headphones, don't do this in modern times. Very high impedance headphones are implied. A neon bulb is useful in many ways in an amateur station, but there are undoubtedly many amateurs who are not aware of the fact that the device can be made to oscillate at either audio or radio frequencies. Fig. 1 shows how a single bulb may be hooked up as an audio frequency oscillator. The L-C circuit is formed by the headphones and a condenser, and by varying the capacity the circuit can be made to oscillate at frequencies from a few cycles per second up to the highest audio frequencies.  The variable resistor in series with the bulb and battery controls the strength of oscillation, and also controls the frequency to some extent. A 1 nf variable condenser will be sufficient to cover most of the audio range.  Fig. 2 The circuit in Fig. 2 may be used when an RF oscillator is to be modulated at audio frequencies. The transformer may be an or...

Radio Exchange Roamer 10 Manual

Image
The Radio Exchange Roamer Ten radio kit from the 1970s perhaps into the early 1980s worked well for me when I was young. Considering the circuit design and the instructions it is unlikely to have worked well for most kit constructors. Nevertheless I got value out of it and it covered a lot of bands. Roamer Ten Manual The circuit design is junk quality but I think it did achieve some design goals such as wide frequency coverage. I can't remember if the version I had included a reduction drive for the tuning capacitor which are difficult to obtain these days and costly as are air gap tuning capacitors.

Transistor Avalanche Pulse Circuit

Image
Transistor avalanche pulse circuits are circuits that use the avalanche effect in a transistor to generate short, high-voltage pulses. The avalanche effect is a phenomenon where a large number of minority carriers are injected into the base region of a transistor, causing a rapid increase in the collector current. This can be used to create very fast pulses, with rise and fall times of less than a nanosecond. Transistor avalanche pulse circuits are typically used in applications where high-speed pulses are required, such as radar, timing circuits, and pulse generators. They can also be used in applications where high-voltage pulses are required, such as laser drivers and high-power switching circuits. Here is a simple example of a transistor avalanche pulse circuit: The main circuit consists of a transistor (Q1), a resistor (R1), and a capacitor (Cc). The capacitor is charged through the resistor until the voltage across the capacitor Cc reaches the breakdown voltage of the transistor....

Free Walsh Hadamard Transform - Free Book

Image
Walsh Hadamard Transform The Fast Walsh Hadamard transform (FWHT) is a powerful tool for signal processing that can be used in a wide range of applications. It is a fast and efficient algorithm that can be used to compress images and audio signals, extract features from signals, and reduce noise from signals. Technical audiences should learn about the FWHT because it is a valuable skill to have in the field of signal processing. The FWHT can be used to improve the performance of many signal processing algorithms, and it is a key component in many signal processing applications. The key to its speed is the reduction in the computational cost afforded by converting the matrix form to simple patterns of addition and subtraction. WHT matrix form. Fast WHT as patterns of addition and subtraction. Download the free WHT EBook