Car NOT Goat
Programming Snapshot – Neural Networks

© Lead Image © Frantisek Hojdysz, 123RF.com
The well-known Monty Hall game show problem can be a rewarding maiden voyage for prospective statisticians. But is it possible to teach a neural network to choose between goats and cars with a few practice sessions?
Here's the problem: In a game show, a candidate has to choose from three closed doors; waiting behind these doors is a car, which is the main prize, a goat, and yet another goat (Figure 1). The candidate first picks a door, and then the presenter opens another, behind which there is a bleating goat. How is the candidate most likely to win the grand prize: Sticking with their choice or switching to the remaining closed door?
As has been shown [1] [2], the candidate is better off switching, because then they double their chances of winning. But how does a neural network learn the optimal game strategy while being rewarded for wins and punished for losses?
Human Model
The input and output data must be professionally manipulated – as is always the case with machine learning. An artificial intelligence (AI) system is not a cauldron into which you throw problems and then ready-made solutions just bubble up. In fact, AI algorithms only solve a small number of precisely defined problems.
To solve the problem, the algorithm used in this article is a multilayer neural network that takes three input parameters: the door the candidate selected, the door the presenter opened, and the remaining locked door.
In the perceptron's hidden middle layer, each artificial neuron is connected to each input neuron of the first layer. Even though a neural network does not quite work like a human brain, you can still interpret these massive links as a reflection of the human design. In turn, each of the hidden layer's inner neurons fires pulses to all the output layer's neurons.
Carrot and Stick
In the training phase, we want the network to learn a strategy from played game shows to predict those that indicated winning the prize on the output neuron, depending on the current door constellation. In a few thousand rounds, the script feeds the three input parameters into the AI system and compares the door value at the output with the actual door leading to the car. If the system has predicted the correct door, it is rewarded. If it is wrong, it has to adjust its neurons' parameters via a feedback mechanism.
In AI jargon, the training runs are called episodes. It is often helpful not to adjust the neuron parameters with every dataset, but instead just after a batch of input values. This saves computing time and prevents the system from balancing the weights in wild swings, which often leads to unstable conditions that don't converge into a solution.
1,000 Shows Recorded
Listing 1 records the results of 1,000 game shows in which the prize is placed behind a random door, and then the presenter opens a door that neither leads to the main prize nor is already open. Game results go to a file in CSV format (Figure 2). It numbers the doors from
to 2
and logs the indices of the following doors in each line in this order: the door that is chosen by the game show candidate, the door that the presenter opens, the remaining door, and the one leading to the prize.
Listing 1
monty

For example, if the neural network encounters the [1,2,0,0]
combination, such as in the first line in the file displayed in Figure 2, it knows that the candidate has chosen the second door (index 1), the presenter has then opened the third (index 2), and the first is still closed (index 0). The main prize was randomly hidden and ended up behind the first door (index 0). With these parameters, to win the game, the neural network must pick the first door.
Listing 1 defines two classes, Door
for individual doors and Show
for a world with three doors and the rules of the TV show. Door
objects are initialized either with or without a main prize; line 15 places the prize behind the first door and then lets line 16 shuffle the doors, so that the prize randomly ends up somewhere. Using the pick()
method from line 22, randrange()
simulates the candidate picking a random door. The Show
object remembers the selected door's index in the picked
instance variable.
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Direct Download
Read full article as PDF:
Price $2.95
News
-
Kali Linux 2022.3 Released
From the creators of the most popular penetration testing distributions on the planet, comes a new release with some new tools and a community, real-time chat option.
-
The 14" Pinebook Pro Linux Laptop is Shipping
After a considerable delay, the 14" version of the Pinebook Pro laptop is, once again, available for purchase.
-
OpenMandriva Lx ROME Technical Preview Released
OpenMandriva’s rolling release distribution technical preview has been released for testing purposes and adds some of the latest/greatest software into the mix.
-
Linux Mint 21 is Now Available
The latest iteration of Linux Mint, codenamed Vanessa, has been released with a new upgrade tool and other fantastic features.
-
Firefox Adds Long-Anticipated Feature
Firefox 103 has arrived and it now includes a feature users have long awaited…sort of.
-
System76 Refreshes Their Popular Oryx Pro Laptop with a New CPU
The System76 Oryx Pro laptop has been relaunched with a 12th Gen CPU and more powerful graphics options.
-
Elive Has Released a New Beta
The Elive team is proud to announce the latest beta version (3.8.30) of its Enlightenment-centric Linux distribution.
-
Rocky Linux 9 Has Arrived
The latest iteration of Rocky Linux is now available and includes a host of new features and support for new architecture.
-
Slimbook Executive Linux Ultrabook Upgrading Their CPUs
The Spanish-based company, Slimbook, has made available their next generation Slimbook Executive Linux ultrabooks with a 12th Gen Intel Alder Lake CPU.
-
Fedora Linux is Coming to the Raspberry Pi 4
Thanks to significant work in the upstream, the upcoming release of Fedora 37 will introduce support for the Raspberry Pi 4.