Suggesting Cooking Recipes Through Simulation and Bayesian Optimization

Garrido-Merchán, Eduardo C.; Albarca-Molina, Alejandro

doi:10.1007/978-3-030-03493-1_30

Cited by 11 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we have seen, the model has several parameters but we do not have an analytic expression to optimize them and computing the mean results can be expensive. Bayesian optimization has been used with success in similar problems [16,8]. In particular, we could optimize several metrics simultaneously under the presence of constraints such as the robot not dying with a constrained multi-objective Bayesian optimization approach [13,17].…”

Section: Methodsmentioning

confidence: 99%

An Artificial Consciousness Model and its relations with Philosophy of Mind

Garrido-Merchán,

Molina,

Mendoza

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This work seeks to study the beneficial properties that an autonomous agent can obtain by implementing a cognitive architecture similar to the one of conscious beings. Along this document, a conscious model of autonomous agent based in a global workspace architecture is presented. We describe how this agent is viewed from different perspectives of philosophy of mind, being inspired by their ideas. The goal of this model is to create autonomous agents able to navigate within an environment composed of multiple independent magnitudes, adapting to its surroundings in order to find the best possible position in base of its inner preferences. The purpose of the model is to test the effectiveness of many cognitive mechanisms that are incorporated, such as an attention mechanism for magnitude selection, pos-session of inner feelings and preferences, usage of a memory system to storage beliefs and past experiences, and incorporating a global workspace which controls and integrates information processed by all the subsystem of the model. We show in a large experiment set how an autonomous agent can benefit from having a cognitive architecture such as the one described.

show abstract

Section: Methodsmentioning

confidence: 99%

An Artificial Consciousness Model and its relations with Philosophy of Mind

Garrido-Merchán,

Molina,

Mendoza

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides the processes described in the previous section and in order to be more general, the proposed architecture uses multimodal information (e.g., ambient music and texts in form of recipes, besides images). These processes would generate subjective creations, which can be correlated with their communication to processes generated in conscious states, such as recipe suggestions [26] where in each position modelled by the GP the robot would find, with a probability sampled from a random variable, a suggestion of a recipe and generate in base of the recipe a degree of tastiness. Another alternative is to include ambient music simulations [42], where in each position in the input space we would have an ambient noise sample, also with a probability distribution given by the sampling of a random variable, and the robot would have a ambient music simulator, that uses these samples to generate music, simulating imagination and conditioning the emotion simulator.…”

Section: An Unified Architecture For the Modelsmentioning

confidence: 99%

A Machine Consciousness architecture based on Deep Learning and Gaussian Processes

Garrido-Merchán¹,

Molina²

2020

Preprint

View full text Add to dashboard Cite

Recent developments in machine learning have pushed the tasks that machines can do outside the boundaries of what was thought to be possible years ago. Methodologies such as deep learning or generative models have achieved complex tasks such as generating art pictures or literature automatically. Machine Consciousness is a field that has been deeply studied and several theories based in the functionalism philosophical theory like the global workspace theory have been proposed. In this work, we propose an architecture that may arise consciousness in a machine based in the global workspace theory and in the assumption that consciousness appear in machines that have cognitive processes and exhibit conscious behaviour. This architecture is based in processes that use the recent Deep Learning and generative process models. For every module of this architecture, we provide detailed explanations of the models involved and how they communicate with each other to create the cognitive architecture. We illustrate how we can optimize the architecture to generate social interactions between robots and genuine pieces of art, both features correlated with machine consciousness. As far as we know, this is the first machine consciousness architecture that use generative models and deep learning to exhibit conscious social behaviour and to retrieve pictures and other subjective content made by robots.

show abstract

“…The most popular example of such an optimization is the task of automatic Machine Learning tuning of the hyperparameters or the hyperparameter problem of machine learning algorithms [19], such as the PC algorithm [4], but also all kinds of subjective tasks like Suggesting Cooking Recipes [7] or other applications belonging to robotics, renewable energies and more [18]. Automatic Hyperparameter Tuning of Machine Learning algorithms is a desirable process that BO can tackle, but the BO procedure also have hyperparameters that need to be fixed a priori.…”

Section: Introductionmentioning

confidence: 99%

Towards Automatic Bayesian Optimization: A first step involving acquisition functions

Merchán,

Pérez

2020

Preprint

View full text Add to dashboard Cite

Bayesian Optimization is the state of the art technique for the optimization of black boxes, i.e., functions where we do not have access to their analytical expression nor its gradients, they are expensive to evaluate and its evaluation is noisy. The most popular application of bayesian optimization is the automatic hyperparameter tuning of machine learning algorithms, where we obtain the best configuration of machine learning algorithms by optimizing the estimation of the generalization error of these algorithms. Despite being applied with success, bayesian optimization methodologies also have hyperparameters that need to be configured such as the probabilistic surrogate model or the acquisition function used. A bad decision over the configuration of these hyperparameters implies obtaining bad quality results. Typically, these hyperparameters are tuned by making assumptions of the objective function that we want to evaluate but there are scenarios where we do not have any prior information about the objective function. In this paper, we propose a first attempt over automatic bayesian optimization by exploring several heuristics that automatically tune the acquisition function of bayesian optimization. We illustrate the effectiveness of these heurisitcs in a set of benchmark problems and a hyperparameter tuning problem of a machine learning algorithm.

show abstract

Suggesting Cooking Recipes Through Simulation and Bayesian Optimization

Cited by 11 publications

References 8 publications

An Artificial Consciousness Model and its relations with Philosophy of Mind

An Artificial Consciousness Model and its relations with Philosophy of Mind

A Machine Consciousness architecture based on Deep Learning and Gaussian Processes

Towards Automatic Bayesian Optimization: A first step involving acquisition functions

Contact Info

Product

Resources

About