# Tic-Tac-Toe and AI: Stacked Multi-Output Model (Part 6)

In our previous blog, we saw that it is possible to provide multiple outputs, each one for a specific use case. So far, the two binary use cases, winning and winner, and the categorical use case, move, do not have any mutual dependencies between them: Their result are all derived from the original inputs. Let’s …

Continue reading ‘Tic-Tac-Toe and AI: Stacked Multi-Output Model (Part 6)’ »

# Tic-Tac-Toe and AI: Wrapping Up the Four Models – Multi-Output (Part 5)

As we have seen in the blog posts before, determining whether a board has a winner, determining which player the winner is, and with which move the winner won the game can all be done using neural networks. These networks only require Dense layers. However, each case has an inherent complexity, so a “minimal” number …

Continue reading ‘Tic-Tac-Toe and AI: Wrapping Up the Four Models – Multi-Output (Part 5)’ »

# Tic-Tac-Toe and AI: And what about the Winning Move? (Part 4)

After having implemented neural networks for determining whether a Tic-Tac-Toe board has a winner or not, and which player the winner is, it is now time to have a look at which is the winning move. Looking at this case, you will notice that there are only three possible cases: Additionally, there is the special …

Continue reading ‘Tic-Tac-Toe and AI: And what about the Winning Move? (Part 4)’ »

# Tic-Tac-Toe and AI: Who is the Winner? (Part 3)

After having determined if a board has a winner using TensorFlow in the previous blog post, let us tackle a very similar question: Who is the winner? Again this is a binary decision: Either X (“0”) or O (“1”) may win a board. It is also possible that we run into a tie, and therefore …

Continue reading ‘Tic-Tac-Toe and AI: Who is the Winner? (Part 3)’ »

# Tic-Tac-Toe and AI: A Winning Board (Part 2)

As a first learning task for using AI with Tic-Tac-Toe, let us take the task of determining whether a board is a winning one or not (i.e. either X or O has won the game). We cannot directly tell the neural network what the rules are for an assignment to be winning. Instead, we need …

Continue reading ‘Tic-Tac-Toe and AI: A Winning Board (Part 2)’ »

# Preparations: Tic-Tac-Toe and AI (Part 1)

You might still remember the times when you played Tic-Tac-Toe (a.k.a. noughts and crosses) in your childhood: In a series of blog posts I want to apply neural networks on this well-known game. But before we may do that, we need to do some preparations. Eventually, we want to teach a neural network to determine: …

Continue reading ‘Preparations: Tic-Tac-Toe and AI (Part 1)’ »

# TensorFlow on GPU: The Memory Hog

By default Tensorflow preallocates GPU memory eagerly. Background for that is that it wants to prevent memory fragmentation. The amount of memory it allocates is around 80% of the memory available. Although running a rather small model with less than 45k of parameters, the monitoring tool nvidia-smi shows this:

# Configuration Files for Kerbal Space Program Plugins

After a little of debugging using “Process Monitor” I figured out that the following plugins store their configuration data at the following places: Plugin Configuration Files are at Kerbal Engineer Redux GameData\KerbalEngineer\Settings\*.xml Toolbar Controller GameData\toolbar-settings.dat I help that this may help also other people to

# Fehler beim Auflösen von DNS-Einträgen im Browser; nslookup funktioniert aber

Wenn alle Browser auf dem Client Fehlermeldungen bringen, daß der DNS nicht aufgelöst werden kann, es aber per nslookup die Anfrage funktioniert, kann das an einer falschen Uhrzeit auf dem DNS-Server/-Proxy liegen. Am DNS-Server können auch folgende Fehlermeldungen auftauchen: Sep 16 07:41:42 raspberrypi named[3538]: no valid RRSIG resolving ‘mozilla.org/DS/IN’: 2001:500:e::1#53Sep 16 07:41:42 raspberrypi named[3538]: validating …

Continue reading ‘Fehler beim Auflösen von DNS-Einträgen im Browser; nslookup funktioniert aber’ »

# Windows 11 ohne Microsoft-Account betreiben

Seit Windows 11 versucht Microsoft immer mehr, einem einen online-aktiven Account für das Betriebssystem anzudrehen. Die Methoden werden immer dreister. Dankenswerterweise hat Heise zwei Möglichkeiten beschrieben, wie man Windows auch ohne Microsoft-Konto betreiben kann. Dabei ist aber noch eine Sache zu beachten: In der Variante “ganz ohne Microsoft-Account” hat man den PC grundsätzlich nicht mit …

Continue reading ‘Windows 11 ohne Microsoft-Account betreiben’ »