Das Video kommt von YouTube: erst beim Abspielen verbindet sich die Seite mit YouTube (Google).
Forward Propagation in Neural Networks | Deep Learning
Das Wichtigste aus dem Video
Tipp auf eine Zeit – das Video springt genau dorthin.
Transkriptautomatisch erstellt · 15 Zeilen
- Let's learn about forward propagation in neural network. We have three layers in a neural network, input, hidden, and output.
- Hidden layer is the layer where the learning happens. Each neuron is activated based on activation functions.
- 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
- information is traversed. Each neuron in first hidden layer does a dot product of the weight and input they receive.
- Then this total is fed to an activation function. And the output of which goes to the next hidden layers.
- This flow repeats until it hits the output layer. In output neuron, activation function is different from the activation functions
- 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
- classification, we can use a sigmoid function at the output layer. If activation is greater than 0.5, then
- one, else zero because sigmoid function ranges between zero and one. This flow of information change depends on the architecture we use.
- 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
- 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
- node. Value at node zero is basically input data into node zero weights. Similarly, value at node one is basically input
- 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
- weights to find the final output. That's all about forward propagation. In the next video, we will learn about back
- propagation in neural networks.
Zum Nachlesen
BackpropagationFehlerrückführung bzw. Rückpropagierung ist ein verbreitetes Verfahren zum Einlernen künstlicher neuronaler Netze. Es gehört in der einfachen Form zur Gruppe …
Künstliches NeuronEin künstliches Neuron bildet die Basis für das Modell der künstlichen neuronalen Netze, ein Modell aus der Neuroinformatik, das durch biologische neuronale …
Künstliches neuronales NetzEin künstliches neuronales Netz besteht aus mehreren künstlichen Neuronen, die miteinander verbunden sind und in der Regel in Schichten organisiert werden. Im …
Multi-Layer-PerzeptronDer Backpropagation-Algorithmus wird oft verwendet, um die Gewichtsaktualisierung zu berechnen. Der Backpropagation-Algorithmus nutzt das Konzept der …