sague Goto Github PK

clasificacion_texto

comparaci-n_rendimiento

derivada_convergencia

dijkstra

ejercicio-4.1

If you know how to program, implement the backpropagation algorithm, that at least will train the following network. If you can do a general implementation of the backpropagation algorithm, go ahead (for any number of neurons per layer, training sets, and even layers). If you do not know how to program, but know how to use a mathematical assistant (such as Matlab or Mathematica), find weights which will suit the following network after defining functions which will ease your task. If you do not have any computing experience, find the weights by hand. The network for this exercise has three neurons in the input layer, two neurons in a hidden layer, and three neurons in the output layer. Usually networks are trained with large training sets, but for this exercise, we will only use one training example. When the inputs are (1, 0.25, -0.5), the outputs should be (1,-1,0). Remember you start with random weights

introduccion-a-julia

milne-algorithm

ordenamiento_topologico

presentacion_julia

python_y_matematicas

rutas-con-restricciones

rutas-cortas