8+2=16106

Patterns

Applicable neurons

• Plus (x + y)
• Minus (x - y)
• Multiple (x × y)
• Division (x ÷ y)
• Connect - two inputs
• Connect - three inputs
• Absolute value
• NAND
• 10000
• Chemical element - atomic number
• character f
• select .... order by .... asc (A, B, C)
• convert HH:MM:SS into hours, minutes, seconds
• If number is without decimal part then X else Y
• mat 33/1
• hejneho matematika 2 - 15/6

Algorithm

Test

/**
 * Plus (x + y): The addition of two whole numbers is the total amount of those quantities combined.
 *
 * @param x1 first number
 * @param x2 second number
 * @return {Array}
 */
function neuron1(x1, x2)
{
math.config({number: 'BigNumber', precision: 64}); return [math.eval(Number(x1) + '+'+Number(x2)).toString()];
}

/**
 * Minus (x - y): 
 *
 * @param x1 Number X
 * @param x2 Number Y
 * @return {Array}
 */
function neuron2(x1, x2)
{
math.config({number: 'BigNumber', precision: 64}); return [math.eval(Number(x1) + '-'+Number(x2)).toString()];
}

/**
 * Connect - two inputs: 
 *
 * @param x1 Variable A
 * @param x2 Variable B
 * @return {Array}
 */
function neuron520(x1, x2)
{
return [x1.toString()+x2.toString()];
}

/**
 * Multiple (x × y): 
 *
 * @param x1 Number X
 * @param x2 Number Y
 * @return {Array}
 */
function neuron3(x1, x2)
{
math.config({number: 'BigNumber', precision: 64}); return [math.eval(Number(x1) + '*'+Number(x2)).toString()];
}

/**
 * Division (x ÷ y): X / Y
 *
 * @param x1 first number
 * @param x2 second number
 * @return {Array}
 */
function neuron17(x1, x2)
{
math.config({number: 'BigNumber', precision: 64}); return [math.eval(Number(x1) + '/'+Number(x2)).toString()];
}

/**
 * Multiple (x × y): 
 *
 * @param x1 Number X
 * @param x2 Number Y
 * @return {Array}
 */
function neuron3(x1, x2)
{
math.config({number: 'BigNumber', precision: 64}); return [math.eval(Number(x1) + '*'+Number(x2)).toString()];
}

/**
 * x to the 2 (x²): x squared
 * 
 * @param x1 Number X
 * @return {Array}
 */
function neuron7(x1)
{
  var outputs = [];
  outputs[0] = x1;

  arr = neuron3(outputs[0], outputs[0]);
  outputs[1] = arr[0];

  return[outputs[1]];
}


/**
 * 5: 
 *
 * @return {Array}
 */
function neuron505()
{
return [5];
}

/**
 * character .: 
 *
 * @return {Array}
 */
function neuron510()
{
return['.'];
}

/**
 * Connect - two inputs: 
 *
 * @param x1 Variable A
 * @param x2 Variable B
 * @return {Array}
 */
function neuron520(x1, x2)
{
return [x1.toString()+x2.toString()];
}

/**
 * Half (0.5): 
 * 
 * @return {Array}
 */
function neuron522()
{
  var outputs = [];

  arr = neuron505();
  outputs[0] = arr[0];

  arr = neuron510();
  outputs[1] = arr[0];

  arr = neuron520(outputs[1], outputs[0]);
  outputs[2] = arr[0];

  return[outputs[2]];
}


/**
 * x to the a  (xª): value of the number x to be the power of a
 *
 * @param x1 x - The base
 * @param x2 a - The exponent
 * @return {Array}
 */
function neuron18(x1, x2)
{
return[Math.pow(Number(x1), Number(x2))];
}

/**
 * Square root (√¯): 
 * 
 * @param x1 Number X
 * @return {Array}
 */
function neuron554(x1)
{
  var outputs = [];
  outputs[0] = x1;

  arr = neuron522();
  outputs[1] = arr[0];

  arr = neuron18(outputs[0], outputs[1]);
  outputs[2] = arr[0];

  return[outputs[2]];
}


/**
 * Absolute value: 
 * 
 * @param x1 Number
 * @return {Array}
 */
function neuron570(x1)
{
  var outputs = [];
  outputs[0] = x1;

  arr = neuron7(outputs[0]);
  outputs[1] = arr[0];

  arr = neuron554(outputs[1]);
  outputs[2] = arr[0];

  return[outputs[2]];
}


/**
 * 8+2=16106: 
 * 
 * @param x1 n1
 * @param x2 n2
 * @return {Array}
 */
function neuron832(x1, x2)
{
  var outputs = [];
  outputs[0] = x1;
  outputs[1] = x2;

  arr = neuron1(outputs[0], outputs[1]);
  outputs[2] = arr[0];

  arr = neuron2(outputs[0], outputs[1]);
  outputs[3] = arr[0];

  arr = neuron520(outputs[2], outputs[3]);
  outputs[4] = arr[0];

  arr = neuron3(outputs[1], outputs[0]);
  outputs[5] = arr[0];

  arr = neuron17(outputs[1], outputs[4]);
  outputs[6] = arr[0];

  arr = neuron2(outputs[1], outputs[6]);
  outputs[7] = arr[0];

  arr = neuron520(outputs[5], outputs[4]);
  outputs[8] = arr[0];

  arr = neuron3(outputs[5], outputs[4]);
  outputs[9] = arr[0];

  arr = neuron17(outputs[8], outputs[8]);
  outputs[10] = arr[0];

  arr = neuron570(outputs[3]);
  outputs[11] = arr[0];

  return[outputs[8]];
}