Flashcards
Terminology
Cards in this deck (6)
- 1InputsAn input vector is the data given as one input to the algorithm. Written as x, with elements x_i, where i runs form 1 to the number of input dimensions, m.
- 2Weights (W_i,j)W_i,j are the weighted connections between nodes i and j. For neural networks these weights are analogous to the synapses in the brain. They are arranged into a matrix W.
- 3OutputsThe output vector is y, with elements y_j, where j runs from 1 the number of output dimensions, n. We can write y(x, W) to remind ourselves that the output depends on the inputs to the algorithm and the current set of weights of the network.
- 4TargetsThe target vector t, with elements t_j, where j runs from 1 to the number of output dimensions, n, are the extra data that we need for supervised learning, since they provide the "correct" answers that the algorith is learning about.
- 5Activation FunctionFor neural networks, g(-) is a mathematical function that describes the firing of the neuron as a response to the weighted inputs.
- 6Error EA function that computes the inaccuracies of the network as a function of the outputs y and targets t.
Information
- Description
- Machine Learning Terminology. This is a test
- Created by
- hvrd1
- Views
- 49
- Tags
- Rating