Deep Learning A-Z™: Artificial Neural Networks (ANN) - Backpropagation
1 like1,328 views
The document describes the process of forward propagation and backpropagation in a neural network. It outlines 7 steps: 1) randomly initializing weights, 2) inputting observations, 3) propagating activations forward, 4) comparing predictions to actual results and measuring error, 5) backpropagating the error to update weights, 6) repeating for each observation or batch, and 7) repeating epochs with the full training set. The goal is to continuously update weights to reduce error through this forward and backward process.
Related topics:1 of 4
More Related Content
What's hot (20)
Ad
Similar to Deep Learning A-Z™: Artificial Neural Networks (ANN) - Backpropagation (20)
Ad
More from Kirill Eremenko (17)
Recently uploaded (20)
Deep Learning A-Z™: Artificial Neural Networks (ANN) - Backpropagation
- 2. © SuperDataScienceDeep Learning A-Z Image Source: neuralnetworksanddeeplearning.com Forward PropagationBackpropagation
- 3. © SuperDataScienceDeep Learning A-Z Neural Networks and Deep Learning Michael Nielsen (2015) Link: http://neuralnetworksanddeeplearning.com/chap2.html Additional Reading:
- 4. © SuperDataScienceDeep Learning A-Z STEP 1: Randomly initialise the weights to small numbers close to 0 (but not 0). STEP 2: Input the first observation of your dataset in the input layer, each feature in one input node. STEP 3: Forward-Propagation: from left to right, the neurons are activated in a way that the impact of each neuron’s activation is limited by the weights. Propagate the activations until getting the predicted result y. STEP 4: Compare the predicted result to the actual result. Measure the generated error. STEP 5: Back-Propagation: from right to left, the error is back-propagated. Update the weights according to how much they are responsible for the error. The learning rate decides by how much we update the weights. STEP 6: Repeat Steps 1 to 5 and update the weights after each observation (Reinforcement Learning). Or: Repeat Steps 1 to 5 but update the weights only after a batch of observations (Batch Learning). STEP 7: When the whole training set passed through the ANN, that makes an epoch. Redo more epochs.