Consider the following table for the connections between the input neurons and the hidden layer neurons.
| Input neuron | Hidden layer neurons | Connection weithts |
| 1 | 1 | 1 |
| 1 | 2 | 0.1 |
| 1 | 3 | -1 |
| 2 | 1 | 1 |
| 2 | 2 | -1 |
| 2 | 3 | -1 |
| 3 | 1 | 0.2 |
| 3 | 2 | 0.3 |
| 3 | 3 | 0.6 |
The connections weights from Hidden layer neurons to the output neurons are 0.5, 0.3 and 0.6 for first, second and third neurons respectively corresponding threshold value for output layer is 0.5 and for hidden layer 1.8, 0.05 and – 0.2 for first, second and third neuron respectively,
(a) Draw the diagraph of the network.
(b) Write the results of activation and interpret.
Assumption: the input neurons have values $x_1=1,\;x_2=1,\;x_3=1$ (not specified in the problem, so I use 1 for each input). The network structure (diagraph) and the numerical activation calculations follow. Diagraph (ASCII): Inputs: I1 I2 I3 Hidden: H1 H2 H3 Output: O Connections (I→H): I1→H1 (weight 1), I1→H2 (0.1), I1→H3 (−1) I2→H1 (1), I2→H2 (−1), I2→H3 (−1) I3→H1 (0.2), I3→H2 (0.3), I3→H3 (0.6) Connections (H→O): H1→O (0.5), H2→O (0.3), H3→O (0.6) Thresholds (compare net sum to these): hidden thresholds __________ ____ _____ ______ _________ ___ _________ _________ ______ ___ ________.
_____ _____ ______ ________ _________ ____ ____ __________ ____ _____.
______ _________ _____ ______ _____ _______ ______ __________.
____ ______ ____ __________ _____ _________ _________.
_________ __________ ___ ________ _____ _________ ________.
___ __________ _____ ___ ______ _______ _________ ___ ______ _______.
____ _________ _____ _____ __________ _______ __________ _______.
____ ________ ___ ________ _____ ______ ________ ________ ______ ___ __________.
__________ ________ ________ __________ _____ __________.
_____ _____ _______ _________ ______ _________ _______ _____ _____ ___ _________ _____.
___ ______ _______ _____ ___ ____ _________ ______.
_________ ____ _____ ________ _____ ___ _____ _____ _______ ___ _________ _____.
_______ __________ _______ _____ ________ ________.
____ __________ __________ ____ ____ ____ _____ ______ ____ _____ ___ ______.
____ _____ _________ _______ _______ _____.
_____ _________ __________ ___ ____ _______ _____ ___.
__________ _____ ________ ________ __________ _______ ___.
__________ _____ ________ ______ ________ _____ ______ _________ _______.
_______ __________ _____ ________ ___.
______ _______ ________ __________ ___ ___.
_______ __________ ____ _________ __________ _____ ___ ____ ____ _________ __________.
______ ____ _______ _____ ____ ________ _______ ___ _____ _______.
_____ ____ _______ __________ _______ _____ ____ ____ _________.
________ ________ __________ ______ ____ _________ __________ _________ __________.
__________ ___ _________ _____ ______ __________ _________.
_____ _____ ____ _______ ______.
__________ _____ _____ _______ ___ ___ ________ __________.
___ ____ __________ __________ ___ ______ _________ ________.
Get Full Answer on WhatsApp
What is the role of loss function in machine learning algorithms? Explain any two commonly used loss functions in machine learning algorithms.
Supervised Learning,
Reinforcement Learning,
If the input vectors arand initial values of three weight vectors are
then calculate the resulting weight found after training the competitive layer with Kohonen’s rule and a learning rate
of 0.5 on the input-series in order I1,I2,and I3,
Semi-supervised.
Consider the following table for the connections between the input neurons and the hidden layer neurons.
| Input neuron | Hidden layer neurons | Connection weithts |
| 1 | 1 | 1 |
| 1 | 2 | 0.1 |
| 1 | 3 | -1 |
| 2 | 1 | 1 |
| 2 | 2 | -1 |
| 2 | 3 | -1 |
| 3 | 1 | 0.2 |
| 3 | 2 | 0.3 |
| 3 | 3 | 0.6 |
Unsupervised learning,