Difference between revisions of "Deep Learning"
Jump to navigation
Jump to search
(Created page with "From a [https://www.datacamp.com datacamp] course. =Concepts= ==Layers== # Input layer # Hidden layer(s); These find interactions between inputs. There can be several layers...") |
|||
Line 24: | Line 24: | ||
'node_1' : np_array([-1,1]), # The first attribute has weight -1 the other 1 | 'node_1' : np_array([-1,1]), # The first attribute has weight -1 the other 1 | ||
'output' : np_array([2,-1]), # Weights for the hidden nodes (node_0 and node_1)} | 'output' : np_array([2,-1]), # Weights for the hidden nodes (node_0 and node_1)} | ||
− | node_0_value = (input_data * weights['node_0']) | + | node_0_value = np.sum(input_data * weights['node_0']) |
− | node_1_value = (input_data * weights['node_1']).sum | + | node_1_value = np.sum(input_data * weights['node_1']) |
+ | layer1_value = np.array([node_0_value,node_1_value]) | ||
+ | output = np.sum(layer1_value * weights['output']) | ||
</syntaxhighlight> | </syntaxhighlight> | ||
+ | |||
+ | ===Rectified Linear Activation Function=== | ||
+ | A ReLU can be used to modify the node's value before it is passed to the next layer. The node will only fire (have a non-zero output value) or fire with more force if the criteria for that are matched. E.g. the output must be positive. |
Revision as of 22:48, 4 December 2018
From a datacamp course.
Concepts
Layers
- Input layer
- Hidden layer(s); These find interactions between inputs. There can be several layers taking input from another layer. The more nodes on a layer the more interactions can be analyzed.
- Output layer
Forward propagation
Hidden node give a value to the input data based on their weight (Input value * weight).
Example:
The amount of children has weight 2 on a hidden node, if there are 3 children 6 will be added to the hidden node. Another attribute on the input layer will add a value to the hidden node too. On another node in the hidden layer the amount of children may have the weight -1, to this node -3 will be added. The values in the nodes in a layer have a weight on the next layer nodes too. Again value * weight is put in the next layer node. A node assigns a weight to each input node. The result of each input value is input * weight. All the results add up to the value of the node.
import numpy as np
input_data = np_array([2,3]) # There are 2 input attributes
weights = {'node_0' : np_array([1,1]), # Both input attributes have weight 1
'node_1' : np_array([-1,1]), # The first attribute has weight -1 the other 1
'output' : np_array([2,-1]), # Weights for the hidden nodes (node_0 and node_1)}
node_0_value = np.sum(input_data * weights['node_0'])
node_1_value = np.sum(input_data * weights['node_1'])
layer1_value = np.array([node_0_value,node_1_value])
output = np.sum(layer1_value * weights['output'])
Rectified Linear Activation Function
A ReLU can be used to modify the node's value before it is passed to the next layer. The node will only fire (have a non-zero output value) or fire with more force if the criteria for that are matched. E.g. the output must be positive.