Created a neural network class from scratch ( without training function ) but predictions are always near 1

Question

I'm new to AI and Neural Networks. I've read a few articles on how to build a neural network from scratch in python so I've decided to build my own.

My code consists of a NN class without a training function that is dynamic in layers. But every time I test it with random numbers the predictions are always greater than 0.7.

What am I doing wrong ?

A little info: layers_counts is a list of integers of neuron counts in each layer, like

(Layer 1: 5 neurons, Layer 2: 3 neurons. -> [5, 3])

import numpy as np


class NeuralNetwork:
    def __init__(self, inputs_count, layers_counts, bias=0):
        self.weights = []
        self.layer_schema = layers_counts
        self.bias = bias
        for lidx, litem in enumerate(layers_counts):
            if lidx == 0:
                self.weights.append(np.random.rand(inputs_count, layers_counts[0]).tolist())
                if len(layers_counts) == 1:
                    break
                else:
                    continue
            self.weights.append(np.random.rand(layers_counts[lidx-1], litem).tolist())

    def train(self, inputs, epochs=100, acc_threshold=0.9):
        todolist = 1

    def predict(self, inputs):
        last_result = 0.0
        last_inputs = inputs
        for layer_c in range(0, len(self.layer_schema)):
            last_inputs = np.dot(last_inputs, self.weights[layer_c])
            last_result = last_inputs + self.bias
        return 1 / (1 + np.exp(-last_result))


net = NeuralNetwork(4, [2, 1, 4], bias=5.3)
print(net.predict([-0.5, 0.3, 0.9, 1]))

Sample results:

[0.99845756 0.99601029 0.99808744 0.99788011]

or

[0.99716477 0.99547246 0.99525549 0.99702588]

Answer 1

It seems to be because you are adding a bias of 5.3 to each layer! This would cause the output to tend towards 1.