Newer
Older
//
//
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
void optimize_via_particle_swarm(l4n::NeuralNetwork& net,
l4n::ErrorFunction& ef) {
/* TRAINING METHOD SETUP */
std::vector<double> domain_bounds(2 * (net.get_n_weights() + net.get_n_biases()));
for (size_t i = 0; i < domain_bounds.size() / 2; ++i) {
domain_bounds[2 * i] = -150;
domain_bounds[2 * i + 1] = 150;
}
double c1 = 1.7;
double c2 = 1.7;
double w = 0.7;
size_t n_particles = 300;
size_t iter_max = 500;
/* if the maximal velocity from the previous step is less than 'gamma' times the current maximal velocity, then one
* terminating criterion is met */
double gamma = 0.5;
/* if 'delta' times 'n' particles are in the centroid neighborhood given by the radius 'epsilon', then the second
* terminating criterion is met ('n' is the total number of particles) */
double epsilon = 0.02;
double delta = 0.7;
l4n::ParticleSwarm swarm_01(
&domain_bounds,
c1,
c2,
w,
gamma,
epsilon,
delta,
n_particles,
iter_max
);
swarm_01.optimize(ef);
net.copy_parameter_space(swarm_01.get_parameters());
/* ERROR CALCULATION */
std::cout << "Run finished! Error of the network[Particle swarm]: " << ef.eval(nullptr) << std::endl;
std::cout
<< "***********************************************************************************************************************"
<< std::endl;
}
double optimize_via_gradient_descent(l4n::NeuralNetwork& net,
l4n::ErrorFunction& ef) {
std::cout
<< "***********************************************************************************************************************"
<< std::endl;
l4n::GradientDescentBB gd(1e-6,
1000,
10000);
gd.optimize(ef);
net.copy_parameter_space(gd.get_parameters());
/* ERROR CALCULATION */
double err = ef.eval(nullptr);
std::cout << "Run finished! Error of the network[Gradient descent]: " << err << std::endl;
/* Just for validation test purposes - NOT necessary for the example to work! */
return err;
}
double optimize_via_LBMQ(l4n::NeuralNetwork& net,
l4n::ErrorFunction& ef) {
size_t max_iterations = 10000;
size_t batch_size = 0;
double tolerance = 1e-4;
double tolerance_gradient = tolerance;
double tolerance_parameters = tolerance;
std::cout
<< "***********************************************************************************************************************"
<< std::endl;
l4n::LevenbergMarquardt lm(
max_iterations,
batch_size,
tolerance,
tolerance_gradient,
tolerance_parameters
);
lm.optimize(ef);
net.copy_parameter_space(lm.get_parameters());
/* ERROR CALCULATION */
double err = ef.eval(nullptr);
// std::cout << "Run finished! Error of the network[Levenberg-Marquardt]: " << err << std::endl;
/* Just for validation test purposes - NOT necessary for the example to work! */
return err;
}
double optimize_via_NelderMead(l4n::NeuralNetwork& net, l4n::ErrorFunction& ef) {
l4n::NelderMead nm(500, 150);
nm.optimize(ef);
net.copy_parameter_space(nm.get_parameters());
/* ERROR CALCULATION */
double err = ef.eval(nullptr);
std::cout << "Run finished! Error of the network[Nelder-Mead]: " << err << std::endl;
/* Just for validation test purposes - NOT necessary for the example to work! */
return err;
}
int main() {
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
try{
/* Specify cutoff functions */
l4n::CutoffFunction2 cutoff2(8);
/* Specify symmetry functions */
l4n::G2 sym_f1(&cutoff2, 0, 0.7);
l4n::G2 sym_f2(&cutoff2, 0.1, 0.8);
l4n::G2 sym_f3(&cutoff2, 0.2, 0.04);
l4n::G2 sym_f4(&cutoff2, 0.3, 0.04);
l4n::G2 sym_f5(&cutoff2, 0.4, 0.04);
l4n::G2 sym_f6(&cutoff2, 0.5, 0.04);
l4n::G2 sym_f7(&cutoff2, 0.6, 0.04);
l4n::G5 sym_f8(&cutoff2, 0.7, -1, 0.9);
l4n::G5 sym_f9(&cutoff2, 0.8, -1, 0.9);
l4n::G5 sym_f10(&cutoff2, 0.9, -1, 0.9);
l4n::G5 sym_f11(&cutoff2, 1, -1, 0.9);
l4n::G5 sym_f12(&cutoff2, 1.1, -1, 0.9);
l4n::G5 sym_f13(&cutoff2, 1.2, -1, 0.9);
l4n::G5 sym_f14(&cutoff2, 1.3, -1, 0.9);
l4n::G5 sym_f15(&cutoff2, 1.4, -1, 0.9);
l4n::G5 sym_f16(&cutoff2, 1.5, -1, 0.9);
l4n::G5 sym_f17(&cutoff2, 1.6, -1, 0.9);
l4n::G5 sym_f18(&cutoff2, 1.7, -1, 0.9);
std::vector<l4n::SymmetryFunction*> helium_sym_funcs = {&sym_f1,
&sym_f2,
&sym_f3,
&sym_f4,
&sym_f5,
&sym_f6,
&sym_f7,
&sym_f8,
&sym_f9,
&sym_f10,
&sym_f11,
&sym_f12,
&sym_f13,
&sym_f14,
&sym_f15,
&sym_f16,
&sym_f17,
&sym_f18};
l4n::Element helium = l4n::Element("He",
helium_sym_funcs);
std::unordered_map<l4n::ELEMENT_SYMBOL, l4n::Element*> elements;
elements[l4n::ELEMENT_SYMBOL::He] = &helium;
/* Read data */
l4n::XYZReader reader("../../data/HE4+T1.xyz", true);
reader.read();
std::cout << "Finished reading data" << std::endl;
std::shared_ptr<l4n::DataSet> ds = reader.get_acsf_data_set(elements);
/* Create a neural network */
std::unordered_map<l4n::ELEMENT_SYMBOL, std::vector<unsigned int>> n_hidden_neurons;
n_hidden_neurons[l4n::ELEMENT_SYMBOL::He] = {20, 20, 1};
std::unordered_map<l4n::ELEMENT_SYMBOL, std::vector<l4n::NEURON_TYPE>> type_hidden_neurons;
type_hidden_neurons[l4n::ELEMENT_SYMBOL::He] = {l4n::NEURON_TYPE::LOGISTIC, l4n::NEURON_TYPE::LOGISTIC, l4n::NEURON_TYPE::LINEAR};
l4n::ACSFNeuralNetwork net(elements, *reader.get_element_list(), reader.contains_charge(), n_hidden_neurons, type_hidden_neurons);
l4n::MSE mse(&net, ds.get());
net.randomize_parameters();
for(size_t i = 0; i < ds->get_data()->at(0).first.size(); i++) {
std::cout << ds->get_data()->at(0).first.at(i) << " ";
if(i % 2 == 1) {
std::cout << std::endl;
}
}
std::cout << "----" << std::endl;
l4n::ACSFParametersOptimizer param_optim(&mse, &reader);
std::vector<l4n::SYMMETRY_FUNCTION_PARAMETER> fitted_params = {l4n::SYMMETRY_FUNCTION_PARAMETER::EXTENSION,
l4n::SYMMETRY_FUNCTION_PARAMETER::SHIFT_MAX,
l4n::SYMMETRY_FUNCTION_PARAMETER::SHIFT,
l4n::SYMMETRY_FUNCTION_PARAMETER::ANGULAR_RESOLUTION};
param_optim.fit_ACSF_parameters(fitted_params, true);
for(size_t i = 0; i < mse.get_dataset()->get_data()->at(0).first.size(); i++) {
std::cout << mse.get_dataset()->get_data()->at(0).first.at(i) << " ";
if(i % 2 == 1) {
std::cout << std::endl;
}
}
std::cout << "----" << std::endl;
// optimize_via_particle_swarm(net, mse);
// optimize_via_NelderMead(net, mse);
double err1 = optimize_via_LBMQ(net, mse);
double err2 = optimize_via_gradient_descent(net, mse);
/* Print fit comparison with real data */
std::vector<double> output;
output.resize(1);
for(auto e : *mse.get_dataset()->get_data()) {
std::cout << "OUTS (DS, predict): " << e.second.at(0) << " ";
net.eval_single(e.first, output);
std::cout << output.at(0) << std::endl;
}
} catch (const std::exception& e) {
std::cerr << e.what() << std::endl;
exit(EXIT_FAILURE);
}
return 0;