Algorithmic Problems & Neural Networks in Python
3.7 (22 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
710 students enrolled
Wishlisted Wishlist

Please confirm that you want to add Algorithmic Problems & Neural Networks in Python to your Wishlist.

Add to Wishlist

Algorithmic Problems & Neural Networks in Python

Learn the basic algorithmic methodologies from backtracking to dynamic programming: Sudoku, Knapsack problem
3.7 (22 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
710 students enrolled
Created by Holczer Balazs
Last updated 3/2017
English
Current price: $10 Original price: $35 Discount: 71% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 5.5 hours on-demand video
  • 5 Articles
  • 3 Supplemental Resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • Understand backtracking
  • Understand dynamic programming
  • Solve problems from scratch
  • Implement feedforward neural networks from scratch
View Curriculum
Requirements
  • Basic Python
Description

This course is about the fundamental concepts of algorithmic problems, focusing on backtracking and dynamic programming. As far as I am concerned these techniques are very important nowadays, algorithms can be used (and have several applications) in several fields from software engineering to investment banking or research&development.

In each section we will talk about the theoretical background for all of these algorithms then we are going to implement these problems together.

The first chapter is about backtracking: we will talk about problems such as N-queens problem or hamiltonian cycles and coloring problem. In the second chapter we will talk about dynamic programming, theory first then the concrete examples one by one: fibonacci sequence problem and knapsack problem.

Who is the target audience?
  • This course is meant for newbies who are not familiar with algorithmic problems in the main or students looking for some refresher
Students Who Viewed This Course Also Viewed
Curriculum For This Course
59 Lectures
05:40:39
+
Introduction
1 Lecture 01:48
+
Backtracking
13 Lectures 01:36:28



Hamiltonian cycle introduction
09:01

Hamiltonian cycle illustration
05:55

Hamiltonian cycle implementation
09:18

Coloring problem introduction
09:12

Coloring problem implementation
06:57

Knight tour introduction
04:06

Knight tour implementation
08:34

Maze problem introduction
03:13

Maze problem implementation
07:59

NP-complete problems
03:51
+
Dynamic Programming
12 Lectures 01:28:54
Dynamic programming introduction
03:22

Fibonacci numbers introduction
05:34

Fibonacci numbers implementation
04:44

Knapsack problem introduction
12:49

Knapsack problem example
13:18

Knapsack problem implementation
07:09

Coin change problem introduction
09:18

Coin change problem example
06:04

Coin change problem implementation
07:18

Rod cutting problem introduction
05:24

Rod cutting problem example
08:14

Rod cutting problem implementation
05:40
+
Neural Network Theory
23 Lectures 02:00:05
---------- NEURAL NETWORKS INTRODUCTION ----------
00:01

Axons and neurons in the human brain
08:22

Modeling human brain
07:25

Learning paradigms
02:59

Artificial neurons - the model
06:58

Artificial neurons - activation functions
06:16

Artificial neurons - an example
05:00

Neural networks - the big picture
04:33

Applications of neural networks
02:12

---------- BACKPROPAGATION ----------
00:01

Feedforward neural networks
08:10

Optimization - cost function
10:40

Simplified feedforward network
08:07

Feedforward neural network topology
06:04

The learning algorithm
05:17

Error calculation
06:06

Gradient calculation I - output layer
08:21

Gradient calculation II - hidden layer
03:49

Backpropagation
05:18

Backpropagation II
01:59

Applications of neural networks I - character recognition
04:06

Applications of neural networks II - stock market forecast
04:10

Deep learning
04:11
+
Neural Network Implementation
7 Lectures 33:18
Neural network implementation - representations
04:20

Neural network implementation - helper methods
03:13

Neural network implementation - initialize
04:56

Neural network implementation - feedforward
04:33

Neural network implementation - backpropagation
07:27

Neural network implementation - mean squared error
03:23

Neural network implementation - testing
05:26
+
Source Code
3 Lectures 00:05
Source code
00:01

Slides
00:01

Coupon codes - get any of my other courses for a discounted price
00:02
About the Instructor
Holczer Balazs
4.5 Average rating
3,133 Reviews
30,909 Students
21 Courses
Software Engineer

Hi!

My name is Balazs Holczer. I am from Budapest, Hungary. I am qualified as a physicist and later on I decided to get a master degree in applied mathematics. At the moment I am working as a simulation engineer at a multinational company. I have been interested in algorithms and data structures and its implementations especially in Java since university. Later on I got acquainted with machine learning techniques, artificial intelligence, numerical methods and recipes such as solving differential equations, linear algebra, interpolation and extrapolation. These things may prove to be very very important in several fields: software engineering, research and development or investment banking. I have a special addiction to quantitative models such as the Black-Scholes model, or the Merton-model. Quantitative analysts use these algorithms and numerical techniques on daily basis so in my opinion these topics are definitely worth learning.

Take a look at my website and join my email list if you are interested in these topics!