About technology

Single Layer Perceptron  – This is the simplest feedforward neural network  and does not contain any hidden layer.  Minsky and Papert mathematically analyzed Perceptron and demonstrated that single-layer networks are not capable of solving problems that are not linearly separable. As they did not believe in the possibility of constructing a training method for networks with more than one layer, they concluded that neural networks would always be susceptible to this limitation. The multilayer perceptron (MLP) is a neural network similar to perceptron, but with more than one layer of neurons in direct power. Such a network is composed of layers of neurons connected to each other by synapses with weights. Learning in this type of network is usually done through the back-propagation error algorithm, but there are other algorithms for this purpose, such as Rprop. However, the development of the backpropagation training algorithm has shown that it is possible to efficiently train

Just continuing with my explanation about Artificial Neural Networks in a simple way. The Adaline  ( Adaptive Linear  Neuron or later  Adaptive Linear Element )  network, proposed by Widrow and Hoff in 1960, has the same structure as the Perceptron, differentiating only in the algorithm of training. She is an adaptive network, with the Inclusion of a pioneering algorithm for the training of  multi-layered networks, the training algorithm of the Delta rule, the Delta rule algorithm is based on the method of least squares, she has a smoother learning method. Their goal is Perform local iterations to get the function and thus set the values of the weights  when the minimum was found. Through an arbitrary point (vector of weights started randomly), the algorithm runs, at each iteration, the surface of the error function towards the point of Minimum. Adaline is a single layer neural network with multiple nodes where each node accepts multiple inputs and generates one output.

In a simple way Artificial Neural Networks are computer models inspired by the nervous system of living beings. My goal is just explain Artificial Neural Networks in a simple way, first we need to start with a little of history: Artificial Neuron Model by McCulloch & Pitts (1943) Hebb Learning Rule (1949) The Perceptron model of Rosenblatt (1958) Discovery of the Perceptron limitation by Minsky and Papert (1969) Hopfield Energy Approach (1982) Backpropagation Learning Algorithm for Perceptron Networks Multiple Layers per Rumelhart (1986) You can find the history in details in these sources: History: The 1940's to the 1970's History: The 1980's to the present The second point is how works a Biological Neuron, a   neuron , also known as a  neurone  (British spelling) and  nerve cell , is an  electrically excitable   cell  that receives, processes, and transmits information through electrical and chemical signals. These signals between neurons occur v

I was working in a new angular application, and I decided to explain the steps that I used for that. The first point is that I was using Ubuntu 64 bits, then i will just explain the steps that I used for that scenario. For start with I choose Visual Studio Code as IDE. To install the program on Ubuntu and still be able to automatically receive future updates from it, you must do the following: Step 1 - Open a terminal (CTRL + ALT + T). Step 2 - Use a command to upgrade as root: sudo su -  Step 3 - Put your password Step 4 - Check if your system is 64-bit, for this, use the following command in the terminal: uname -m Step 5 - If your system is 64-bit, add the program repository with this command or use this tutorial: sudo sh -c 'echo' deb [arch = amd64] https://packages.microsoft.com/repos/vscode stable main "> /etc/apt/sources.list.d/vscode.list ' Step 6 - Download and install the program repository key, using the commands below: curl https: