Centre for Artificial Intelligence Research (CAIR) photo

cair Goto Github PK

Name: Centre for Artificial Intelligence Research (CAIR)

Type: Organization

Bio: CAIR is a centre for research excellence on artificial intelligence at the University of Agder. We attack unsolved problems, seeking superintelligence.

Location: Grimstad, Norway

Blog: https://cair.uia.no/

Cair Platform

This package providies you with three components to manage the content on your website:

Platform: A dynamic active record implementation. Allowing you to configure your data structure at runtime.
Access: A restful JSON API used by the admin panel or by your application.
Panel: The admin panel for filling in your data.

Installation

Via composer.

{
    "require": {
        "cair/cair": "0.1.*",
        "stack/builder": "1.0.*",
        "stack/url-map": "1.0.*"
    }
}

composer update

And bower.

bower install cair-panel

Usage

// Create your application in $app.

Cair\Platform\Provider::setConfig([
  'resources' => [
		'posts' => [
			'attributes' => ['title', 'content'],
			'rules' => [
				'title' => ['required', 'min' => 3],
				'content' => ['required']
			],
			'types' => [
				'title' => 'text',
				'content' => 'textarea',
			]
		]
	],
	'scripts' => [
		"panel/dist/js/cair.js"
	]
]);

$stack = new Stack\Builder;

$stack->push('Stack\UrlMap', [
    '/admin' => require(__DIR__.'/src/Cair/Panel/start.php'),
    '/api' => require(__DIR__.'/src/Cair/Access/start.php'),
]);

$app = $stack->resolve($app);

$request = Request::createFromGlobals();

$app->handle($request)->send();

Centre for Artificial Intelligence Research (CAIR)'s Projects

an-optimized-toolbox-for-advanced-image-processing-with-tsetlin-machine-composites

An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites

awesome-tsetlin-machine

A curated list of Tsetlin Machine research

convolutional-tsetlin-machine-tutorial

Tutorial on the Convolutional Tsetlin Machine

corrembed_evaluating_pre-trained_model_efficacy

Code for the paper "CorrEmbed: Evaluating Pre-trained Model Efficacy with a Novel Metric Integrating Image Embedding and Tag Correlation"

deep-rts

A Real-Time-Strategy game for Deep Learning research

deep-warehouse

A Simulator for complex logistic environments

deepaxie

Implementation of a simplified Axie Infinity Environment in C++ that is used to train an agent with the reinforcement learning algorithm DQN to play the game.

Due to the high energy consumption and scalability challenges of deep learning, there is a critical need to shift research focus towards dealing with energy consumption constraints. Tsetlin Machines (TMs) are a recent approach to machine learning that has demonstrated significantly reduced energy usage compared to neural networks alike, while performing competitively accuracy-wise on several benchmarks. However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game. In this paper, we propose a novel finite-state learning automaton that can replace the Tsetlin Automata in TM learning, for increased determinism. The new automaton uses multi-step deterministic state jumps to reinforce sub-patterns. Simultaneously, flipping a coin to skip every d'th state update ensures diversification by randomization. The d-parameter thus allows the degree of randomization to be finely controlled. E.g., d=1 makes every update random and d=infinity makes the automaton completely deterministic. Our empirical results show that, overall, only substantial degrees of determinism reduces accuracy. Energy-wise, random number generation constitutes switching energy consumption of the TM, saving up to 11 mW power for larger datasets with high d values. We can thus use the new d-parameter to trade off accuracy against energy consumption, to facilitate low-energy machine learning.

cair Goto Github PK

Cair Platform

Installation

Usage

Centre for Artificial Intelligence Research (CAIR)'s Projects

Recommend Projects

Recommend Topics

Recommend Org

Jobs