NicolaBernini

#include <iostream>
#include <boost/system/error_code.hpp>
#include <boost/asio.hpp>
#include <boost/bind.hpp>
#include <boost/date_time/posix_time/posix_time.hpp>

/**
  * @brief The Timer Callback Function which reschedule the timer after 1 sec for 5 times 
  */
void callback_func(const boost::system::error_code& e, boost::asio::deadline_timer* pt, int* pcont)

NicolaBernini

Overview

An Artificial Neural Network (ANN) with a Multi-Layer Structure can be seen as a Cascade of Linear Combinations of Neurons Transfer Functions

In case of a Binary Classification Task the implicit goal for the ANN is to learn a Function which separates the ANN Input Space in 2 regions: one for each possible label. Let's call this function the Input Space Separation Function.

What if the Neuron Transfer Function would be linear ?

In that case the ANN would only be able to learn a Linear Input Space Separation Function hence

NicolaBernini

NicolaBernini

#include <stdio.h>
#include <fstream>
#include <stdexcept>
#include <memory>

class URL2File
{

NicolaBernini

Overview

This is a solution to the Interval Coverage Detection Problem, based on the idea of recursively fusing segments

More details in the Medium Article

NicolaBernini

import tensorflow as tf
from matplotlib import pyplot as plt
dataset = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = dataset.load_data()

# Check it works by plotting a number 
plt.imshow(x_train[0])

NicolaBernini

# Specs for Naive Hashing 
# - Input: String 
# - Output: Array id 
# - Naive Hashing Function: sum all the string letters and mod for array size to get an id 

def hash_str(in_str, in_lin_storage_size): 
    full_hash_val=0
    if(type(in_str) is not str): 
        raise(ValueError("Arg1 needs to be string"))
    for c in in_str: 

NicolaBernini

Overview

The problem is a generalization of the one explained in How to find the 3rd element from end in linked list in Java and basically consists of finding the element at position last - n in a Linked List which of course does not provide

• Random Access Semantic

• Length Semantic

but just the next() semantic

NicolaBernini

# Defines a WxHxC ConvFilter 
# Conventional Internal Representation is C,H,W 
class Conv: 
  # w, h = Kernel Spatial Domain 
  # in_c = Input Tensor Channels 
  # out_c = Output Tensor Channels 
  def __init__(self, w, h, in_c, out_c): 
    self.w = w 
    self.h = h 

NicolaBernini

#include <iostream>
#include <vector>
#include <array>
using namespace std;

// Performing element-wise comparison on a containers pair with the same number of elements and returning a vector where for the i-th position 
// the -1 means the i-th element in the first is bigger than the i-th in second 
// the +1 means the i-th element in the second is bigger than the i-th in the first 
// the 0 means the i-th elements in first and second can not be ordered hence it is assumed they are equal (but no explicit use of the equal semantic is done)
template <typename T>