Zum Inhalt springen
L

Das Video kommt von YouTube: erst beim Abspielen verbindet sich die Seite mit YouTube (Google).

Forward Propagation in Neural Networks | Deep Learning

Satyajit Pattnaik2:39 69.578 Aufrufe veröffentlicht Auf YouTube

Das Wichtigste aus dem Video

Tipp auf eine Zeit – das Video springt genau dorthin.

Transkriptautomatisch erstellt · 15 Zeilen
Herunterladen
  1. Let's learn about forward propagation in neural network. We have three layers in a neural network, input, hidden, and output.
  2. Hidden layer is the layer where the learning happens. Each neuron is activated based on activation functions.
  3. Forward propagation is the movement of information from input to the output layer via the hidden layers. At a very high level, this is how the
  4. information is traversed. Each neuron in first hidden layer does a dot product of the weight and input they receive.
  5. Then this total is fed to an activation function. And the output of which goes to the next hidden layers.
  6. This flow repeats until it hits the output layer. In output neuron, activation function is different from the activation functions
  7. used in the hidden layer neurons. This activation functions depends on the task which we are doing. For example, if we are doing a binary
  8. classification, we can use a sigmoid function at the output layer. If activation is greater than 0.5, then
  9. one, else zero because sigmoid function ranges between zero and one. This flow of information change depends on the architecture we use.
  10. But the general idea is same. Let's see how forward propagation works for a single data point. This is a program to understand the
  11. concept. We have two nodes of a hidden layer. We have an input which is one and two. We have defined the weights at each
  12. node. Value at node zero is basically input data into node zero weights. Similarly, value at node one is basically input
  13. data multiplied with node one weights. Similarly, hidden layer results is done by adding value one and value two. And then it is multiplied with output
  14. weights to find the final output. That's all about forward propagation. In the next video, we will learn about back
  15. propagation in neural networks.

Zum Nachlesen