You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -17,8 +19,8 @@ DN2A aims to allow you to create and train simple Neural Networks as well as ver
17
19
-**Modularized components**: helps the development and the clear separation of concerns with great benefits for who wants to use mixed solutions.
18
20
-**Configurable computation precision**: helps to avoid the noise deriving from operation errors and default system precision limits with great improvement of the learning speed and performance stability.
19
21
-**Configuration checker**: helps to write less details about configuration and to keep compatibility with older version while the project evolves.
20
-
-**StepByStep or Continuous training**: helps to train neural networks without being limited to a particular approach for the greater good of projects with very complex project's needs.
21
-
- TODO (Bios) **Data normalization**: helps to simplify the interaction within your real domain.
22
+
-**StepByStep or Continuous training**: helps to train neural networks without being limited to a particular approach for the greater good of projects with very complex project's needs.
23
+
- TODO (Bios) **Data normalization**: helps to simplify the interaction within your real domain.
22
24
- TODO (Host) **Networks composition**: helps to create very effective architectures of multiple neural networks able to obtain advanced behaviours like in deep learning.
23
25
- TODO (Host) **Computation parallelization**: helps to improve the scalability of your whole system.
24
26
- TODO (Bios) **Sessions intercommunication**: helps to improve the scalability of your whole system.
@@ -126,12 +128,12 @@ To import through your preferred loader configure it to point to the right place
126
128
127
129
### Training/Querying a Network with default parametrization ###
128
130
129
-
// Importation
131
+
// Importation
130
132
var DN2A = require("dn2a");
131
-
133
+
132
134
// Instantiation
133
135
var neuralNetwork = new DN2A.NetworkAlpha();
134
-
136
+
135
137
// Training
136
138
var trainingPatterns = [
137
139
{
@@ -152,7 +154,7 @@ To import through your preferred loader configure it to point to the right place
152
154
}
153
155
];
154
156
neuralNetwork.train(trainingPatterns);
155
-
157
+
156
158
// Querying
157
159
//
158
160
// The object passed to the callback function contains information about the querying process.
@@ -172,13 +174,13 @@ To import through your preferred loader configure it to point to the right place
172
174
173
175
// Importation
174
176
// ...
175
-
177
+
176
178
// Instantiation
177
179
//
178
-
// The object passed to the constructor function contains properties describing the neural network.
180
+
// The object passed to the constructor function contains properties describing the neural network.
179
181
// The list of the properties is reported in the main README file.
180
-
// In case one or more properties are not present they are substituted with defaults.
181
-
// Same thing happens if the object is not passed at all.
182
+
// In case one or more properties are not present they are substituted with defaults.
183
+
// Same thing happens if the object is not passed at all.
182
184
var neuralNetwork = new DN2A.NetworkAlpha({
183
185
layerDimensions: [2, 4, 4, 1], // the default would be [2, 4, 1]
184
186
learningMode: "continuous",
@@ -195,21 +197,21 @@ To import through your preferred loader configure it to point to the right place
195
197
},
196
198
numbersPrecision: 32
197
199
});
198
-
200
+
199
201
// Training
200
202
// ...
201
-
203
+
202
204
// Querying
203
205
// ...
204
206
205
207
### Training/Querying a Network with evolution feedback ###
206
208
207
209
// Importation
208
210
// ...
209
-
211
+
210
212
// Instantiation
211
213
// ...
212
-
214
+
213
215
// Training
214
216
//
215
217
// The object passed to the callback function contains information about the training process.
@@ -235,15 +237,15 @@ To import through your preferred loader configure it to point to the right place
0 commit comments