Jorge G PiresCenter of Excellence for Research DEWS (University of L'Aquila, DISIM, Italy) · Ingegneria e scienze dell'informazione e matematica
Jorge G Pires
PhD
IdeaCodingLab.tech/JovemPesquisador.com, Udemy, YouTube, Amazon, Google Books, Superprof
About
93
Publications
38,219
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
99
Citations
Introduction
B.Eng by Universidade Federal de Ouro Preto (Brazil) in Production Engineering; double master degree by University of L'Aquila and Gdansk University of Technology: PhD on a collaboration between the Brazilian programme Science without Borders in biomathematics at the University of L'Aquila/IASI-CNR/BioMathLab. Master of science and PhD degrees recognized in Brazil by the University of São Paulo (USP) as bioinformatics. Postdoc by Federal University of Bahia.
Additional affiliations
May 2019 - December 2020
Position
- PostDoc Position
Description
- On this postdoctoral fellowship, I have focused on designing a user-friendly interface for computational biology, for potential application to a startup on target therapy (precision medicine).
November 2017 - December 2018
Position
- PostDoc Position
Description
- On this postdoctoral fellowship, I have focused on biomedical image segmentation. Postdoc position by PNPD-CAPES.
January 2014 - March 2017
Education
January 2014 - March 2017
Publications
Publications (93)
The ambition of this document is to set in evidence the prerequisite for integrative (mathematical) models, mechanism-based models, for appetite/bodyweight control. For achieving this goal, it is provided a scrutinized literature review and it is organized them in such a way to make the point. The quantitative methods exploited by the authors are c...
Desde o seu desvendamento em 1994, leptina tem sido um hormônio (neuroendócrino) amplamente averiguado. No entanto, estudos até o momento têm sido tendenciosos a experimentos e relatos, existe uma deficiência de modelos integrados, arquétipos que coloquem achados múltiplos em um sistema integrado como "humano virtual". Esse tipo de aparelhagem prom...
Amongst the entire potential spectrum
of expansion of the engineering
sciences as an omnipresent field, we
might point out the studies of drugs,
applied pharmacology, as a good
candidate for receiving attention. The
common problematic encountered in the
literature faced by the industry of drugs
is the high cost for drug development
and systematic a...
The peer review process is the cornerstone of modern science. No scientist can move on the scientific world without having to face this wall. On this paper, I talk about my own experience with the system and I connect it with the literature on the topic. There are several researchers presenting criticism on the system, and possible solutions. I am...
Introduction: Despite the ubiquity of statistics in numerous academic disciplines, including life sciences, many researchers–who are not statistically trained–struggle with the correct application of statistical analysis, leading to fundamental errors in their work. The complexity and importance of statistics in scientific research necessitate a to...
Conversational Artificial Intelligence (CAI) was the latest big step towards artificial general intelligence (AGI): models of AI that are generic, that can solve problems without being restricted to a small set of problems they were designed for. OpenAI with chatGPT gave a big step towards this direction. On the other hand, being able to classify s...
Artificial Intelligence (AI) evolved in trends. Currently, the trend is Conversational Artificial Intelligence (CAI). Those models of AI are focused on text-related tasks, and their commonest applications are chatbots. On this paper, we explore a smart chatbot using the Large Language Models (LLMs) from openAI. I have used a tool called Teachable M...
UNSTRUCTURED
Artificial Intelligence (AI) evolved in trends. Currently, the trend is Conversational Artificial Intelligence (CAI). Those models of AI are focused on text-related tasks, and their commonest applications are chatbots. On this paper, we explore a smart chatbot using the Large Language Models (LLMs) from openAI. I have used a tool calle...
Even though statistics is taught in several courses, including life sciences, their applications tend to be challenging; basics errors are inevitably done by researchers. It is not uncommon discussions on errors done during statistical analysis done on data by non-experts in statistics, in scientific papers. However, statistics is too important and...
Introduction: deep learning emerged in 2012 as one of themost important machine learning technologies, reducing image identification error from25% to 5%. This article has two goals: 1) to demonstrate to the general public the ease of building state-of-the-art machine learningmodels without coding expertise; 2) to present a basicmodel adaptable to a...
Conversational Artificial Intelligence (CAI) was the latest big step towards artificial general intelligence (AGI): models of AI that are generic, that can solve problems without being restricted to a small set of problems they were designed for. OpenAI with chatGPT gave a big step towards this direction. On the other hand, being able to classify s...
Introduction
Contributions to medicine may come from different areas; and most areas are full of researchers wanting to support. Physists may help with theory, such as for nuclear medicine. Engineers with machineries, such as dialysis machine. Mathematicians with models, such as pharmacokinetics. And computer scientists with codes such as bioinform...
Introduction: Contributions to medicine may come from different areas; and most areas are full of researchers wanting to support. Physists may help with theory, such as for nuclear medicine. Engineers with machineries, such as dialysis machine. Mathematicians with models, such as pharmacokinetics. And computer scientists with codes such as bioinfor...
![Figure 1. Neural networks are ruler finders. Source: [11]](profile/Jorge-Pires-6/publication/371540786/figure/fig1/AS:11431281167717858@1686740879806/Neural-networks-are-ruler-finders-Source-11_Q320.jpg)
Introduction: deep learning emerged in 2012 as one of the most important machine learning technologies, reducing image identification error from 25% to 5%. This article has two goals: 1) to demonstrate to the general public the ease of building state-of-the-art machine learning models without coding expertise; 2) to present a basic model adaptable...
Introduction
deep learning emerged in 2012 as one of the most important machine learning technologies, reducing image identification error from 25% to 5%. This article has two goals: 1) to demonstrate to the general public the ease of building state-of-the-art machine learning models without coding expertise; 2) to present a basic model adaptable t...
Uma das grandes limitações atuais do chatGPT API para desenvolvedores é o tamanho máximo da chamada de API, um pouco acima de 4.000 tokens; melhor do que o GPT-3, em torno de 2.000. Independente se no futuro isso for melhorado, sugiro evitar enviar um arquivo de 30 páginas para responder perguntas: isso custa, além de muito provavelmente aumentar o...
Computational thinking is evolving on a speed that even someone working with it daily can be surprised with their ever-changing state. On this short essay, we shall consider the place of chatGPT in medicine. chatGPT can be seen as a medical assistant, where the medical doctor can base their initial thoughts, for posterior enhancements. We claim tha...
Prezados, esse é um dos capítulos do meu ebook Ciência para Não Cientista. O objetivo é oferece um pouco de pensamento científico ao público leigo. Nesse capítulo, eu discuto as formas de pensamento.
Neste anexo do livro Mercado da Criatividade, falo da minha experiência com o ciência sem fronteias, e um pouco da minha tristeza do programa ter desaparecido.
Vamos falar um pouco da relação entre o jovem pesquisador e as redes sociais.
How much do we have to know to predict? do not mistake understanding with prediction! The illusion of validity hortly: not much! and here goes my rationale with all the nuances of the issue! Stick around before making your opinion! Better, make your opinion first and compare your notes with my thinking patterns, and let me know your thoughts! I am...
Uma vez foi sabiamente dito "Mathematics are the lens by which we see reality" e
“Mathematics is the new microscope, however, even better".
Métodos matemáticos e computacionais têm sido uma ferramenta cada vez mais potente quando aplicada às ciências da vida, especialmente devido ao baixo custo dos computadores nos dias atuais, e cada vez mais pot...
Angular is a Google framework: it is a Single Application Page (SPA) generator.
With Angular, you can build apps that runs on browsers (frontend), no need of backend frameworks/libraries such as Express/Node.js/NestJS. With current achievements by the Angular community, you can now do essentially anything on the frontend. Recently, Firebase, also...
Neste relatório final de pós-doutorado, falo do meu período de pós-doutoramento pela CDTS/Fiocruz. Desenvolvi uma plataforma em MEAN stack, uma interface amigável para simulação de biologia computacional.
Preprint, submetido à Revista Docência do Ensino Superior. Uma introdução aos métodos matemáticos nas ciências da vida: um relato de experiência com e-learning e ensino presencial
Resumo: Objetivo deste trabalho é apresentar os resultados do desenvolvimento de um curso cujo objetivo é oferecer a cientistas da vida uma porta de entrada para o mund...
One aspect of personalized medicine is aiming at identifying specific targets for therapy considering the gene expression profile of each patient individually. The real-world implementation of this approach is better achieved by user-friendly bioinformatics systems for healthcare professionals. In this report, we present an online platform that end...
One aspect of personalized medicine is aiming at identifying specific targets for therapy considering the gene expression profile of
each patient individually. The real-world implementation of this approach is better achieved by user-friendly bioinformatics
systems for healthcare professionals. In this report, we present an online platform that end...
Body weight control is gaining interest since its dysregulation eventually leads to obesity and metabolic disorders. An accurate mathematical description of the behavior of physiological variables in humans after food intake may help in understanding regulation mechanisms and in finding treatments. This work proposes a multi-compartment mathematica...
Atualmente, a taxa de empreendedorismo da população adulta brasileira é 38%, realidade que pode propiciar a criação de startups. Não existe uma definição única para startup, mas a visão mais aceita a define como um ‘modelo de negócio’ interino, cujo objetivo é alcançar um modelo de negócio escalável e repetitivo. O objetivo principal deste artigo é...
Nos últimos anos, tem havido um crescimento, quase exponencial, dos custos com saúde. Como consequência, formas diversas têm sido propostas e implementadas para lidar com as demandas na área de saúde. Nos tempos atuais, estas demandas envolvem tratamentos cada vez mais eficientes, personalizados, acessíveis e de baixo custo. Diante deste cenário, p...
Modelagem matemática de câncer/tumor: seria o mais novo aliado na luta contra o câncer/tumor? Nas últimas décadas, tem havido um aumento significativo no diagnóstico (precoce) de câncer em todo o mundo. Segundo o INCA (Instituto Nacional de Câncer), os casos de câncer ficaram somente atrás de doenças cardiovasculares como motivo de óbitos em 2008....
O uso de conceitos matemáticos nas ciências da vida tem sido de grande valia nas últimas décadas, com aplicações desde a medicina à biologia. A Teoria dos Jogos (game theory) foi inicialmente aplicada à área de economia, onde um conjunto de indivíduos tomam decisões, e essas decisões afetam a todos, criando conceitos como Equilíbrio de Nash. Neste...
O emprego de imagens está cada vez mais presente nos tempos atuais, especialmente nas áreas médicas e de visão computacional; e segmentação de imagens é uma metodologia largamente empregada para se fazer bom uso dessas imagens. Conceitualmente, segmentação de imagens é parte de quase todos esquemas computacionais para reconhecimento de padrão em im...
On this short presentation, I have presented the stochastic version the ghrelin model.
This is the first slide of a short course given to the 1st Conference on Statistics and Data Science. http://www.csds.ime.ufba.br/short_courses.html
Food intake, bodyweight and appetite are controlled by a “web of hormones.” Recently, from this aforementioned web of hormones, several hormones have been revealed and investigated from a
medical standpoint with different degrees of success: a key one is ghrelin. Accordingly, ghrelin is an orexigenic (i.e., appetite stimulant) hormone; in fact, the...
![Fig. 3. Schematic view of our hybrid algorithm (Source: Pires, 2017 [1])](profile/Jorge-Pires-6/publication/321082054/figure/fig2/AS:631631618506757@1527604121137/Schematic-view-of-our-hybrid-algorithm-Source-Pires-2017-1_Q320.jpg)
Food intake, bodyweight and appetite are controlled by a “web of hormones.”On this work, we shall present a problem in parameter estimation using evolutionary algorithms alongside local search, what we have called hybrid algorithms (global search + local search); furthermore, we apply artificial neural networks (feedforward neural network) for supp...
Ghrelin, a peptide hormone, occupies a crucial role in food intake control. Differently from other hormones contributing to energy homeostasis, usually exerting their regulating action by signaling satiety (e.g. leptin), ghrelin is known to stimulate appetite and, in general, to upsurge the propensity of animals to seek out food and start eating. M...
Ghrelin, a peptide hormone, occupies a crucial role in food intake control. Differently from
other hormones contributing to energy homeostasis, usually exerting their regulating action by
signaling satiety (e.g. leptin), ghrelin is known to stimulate appetite and, in general, to upsurge
the propensity of animals to seek out food and start eating. M...
Ghrelin, a peptide hormone, occupies a crucial role in food intake control. Differently from other hormones contributing to energy homeostasis, usually exerting their regulating action by signaling satiety (e.g. leptin), ghrelin is known to stimulate appetite and, in general, to upsurge the propensity of animals to seek out food and start eating. M...
The elegant ‘interconnected mechanisms’ by which the gastrointestinal (GI) tract regulates food intake are a marvel of biology, but the redundancy (e.g., several hormones seem to have effects in food intake) of both GI (by means of hormones) and central nervous system (CNS, by means of satiety/satiation signals) pathways governing energy homeostasi...
Abstract The methodology of design and development of new products has been around for a while and applied to the industry for decades with pretty good results. The results were so positive that nowadays one can find quite a few courses, books, papers and alike. On the other hand, the university seems not being able to cope with the digital generat...
Abstract Ghrelin is a quite powerful hormone discovered in the end of the 1990s that controls appetite and energy homeostasis, alongside leptin and other hormones still to be investigated in depth by the medical sciences literature. On this poster we provide a simple mathematical model, consisting of a set of ordinary differential equations detaili...
This some technical details for "A crash course in biomathematics"
On this set of slides we discuss an ongoing project that aims at proposing a course in biomathematics. We will apply well-known methodologies from the industry for designing the course, that is to say, design and development of new products. Our eminent goal is a prototype, which is the watershed for the second stage of the project, nonetheless ind...
This is the last talk of my PhD project, second year. On this talk, we discuss the first model, which gave rise to our first paper.
Entre as maiores revoluções do século vinte jaz a mutação de como se vê e modela a realidade que nos rodeia. O escopo do trabalho é chamar a atenção de cientistas em geral para a área de modelagem estocástica. A motivação é a aparente falta de interesse pela modelagem estocástica por cientistas de algumas áreas. Umas das maiores questões não-respon...
This is a set of slides I have used in one of my "talks" (report) regarding my current research on ghrelin-leptin-insulin mathematical modelling.
This is a set of slides I have used as part of a four-section talk I have given in June 2014, as part of the report of my research progresses.
Resumo. Controle de peso é um vultoso desafio para qualquer pessoa. Ordinariamente, apreensão com relação a controle de peso abrolha tanto devido a fatores estéticos como de bem-estar. Umas das maiores problemáticas jaz na ocorrência de que o processo de alimentar e controle interno de energia, chamado cientificamente de homeostase, é alcançado de...
Resumo. Controle de peso é um vultoso desafio para qualquer pessoa. Ordinariamente, apreensão com relação a controle de peso abrolha tanto devido a fatores estéticos como de bem-estar. Umas das maiores problemáticas jaz na ocorrência de que o processo de alimentar e controle interno de energia, chamado cientificamente de homeostase, é alcançado de...
on this manuscript, we report the proposal of the
use of computational intelligence methods as a powerful and
valuable source of mathematical tools for modeling gene
expression networks. Gene expression networks are modeled via
transcription networks. Transcription networks are graphoriented
mathematical-computational models that attempt to
underst...
This is a set of slides I have used when I have given a talk that led to my thesis of master of science, at the IASI-CNR Rome.
This is a set of slides from the Talk I have given in 2012, L'Aquila, as a Mathmods (Double Diploma) student. The full text was published as well.
Redes neurais, de forma mais específica, redes neurais artificiais são técnicas empregadas em engenharias já de algum tempo. Este livro busca tratar essas técnicas de forma simples, sem minudências. A ideia é trazer essas ferramentas cada vez mais onipresentes nas nossas vidas, independente da formação acadêmica, para um plano "vulgar".
On this manuscript, we report the proposal of the use of computational intelligence methods, in special neural networks, as a powerful and valuable source of mathematical tools for modelling gene expression networks. With respect to the state of the art, gene expression networks are modelled via transcription networks which are graph-oriented mathe...
Resumo:
Biologia Sistêmica possui como um dos seus objetivos principais unir acadêmicos com formações e interesses diferentes como: matemáticos, físicos, biólogos, cientistas da computação, médicos, e outros profissionais de forma unificada e integrada; essa tentativa de unificação do conhecimento cria desafios e promessas. Uma análise rápida da li...
Abstract -- In recent scientific endeavors, science has learnt that not all systems can be understood satisfactorily in a reductionism-
like approach; ‘the sum of the parts makes up the all’ does not hold for all systems. Nowadays, biology has worked in synergy
with fields such as mathematics and computer sciences for making sense of those Complex...
Abstract- The vitreous detachment is an ophthalmologic-physiological disorder associated in general to aging-side effects
and on the current paper numerical inference on the disorder via molecular dynamics methods is reported in synergy with
literature survey on the issue. Regarding the place of the reported scientific achievement, it contributes f...
![Fig. 5. Cancer cell population for model, the one discussed in [12],...](profile/Jorge-Pires-6/publication/280877647/figure/fig4/AS:613444982169642@1523268089429/Cancer-cell-population-for-model-the-one-discussed-in-12-called-linear-and-the-one_Q320.jpg)
Abstract. This paper is the formal mixture of three different areas of
knowledge, two from applied math and engineering, and one from applied
medicine and pharmacology. The aforementioned areas are: optimal control
theory, evolutionary algorithms, and finally pharmacokinetic/pharmacodynamic
modeling, PK/PD for short. We design and test a computer p...
Abstract. Since its "foundation," computational intelligence has been creating
novel-high perspectives on modeling, on the other hand, the "old-fashioned"
mathematics offers powerful methods that should not be forgotten or underestimated.
On this paper, it is discussed a novel methodology proposed by the authors
on the mathematical modeling, with e...
This is the slides I have used in one of my discussions at the BioMathLab-IASI-CNR. That was the second from a series of discussions that led me to the current state of the art on my PhD research. The basic idea was to present the several hormones I have studied and discuss a paper that was given to me months ago about leptin, mathematical modellin...
Herein we discuss a mathematical for ghrelin dynamics based on material science. It was presented to the group of BioMathLab Gemelli Hospital, the group I am working with right now as a PhD student. The current models are a little bit different, but the core idea was kept.
On this work it is discussed on the optimal control theory as supplementary and complementary methodological procedure to operations researches. Accordingly, it is disserted on the importance of optimal control theory as an essential tool for supporting operations research on its chases for enhancing processes by means of optimization. Here two cas...
Abstract— with the advent of computers, new technologies could finally be applied properly. Maybe one of the most polemic and prominent ones are the methods from artificial intelligence such as neural networks or even fuzzy logic.
In this short paper we discuss a set of insights generated by the author after studying the two-communities currently...
with the advent of computers, new technologies could finally rise up. Maybe one of the most polemic and prominent ones are the methods from artificial intelligence such as neural networks or even fuzzy logic. In this short paper we discuss a set of insights generated by the authors after studying the two-communities currently predominant in applied...
Life Sciences might be seen as the connections between medicine, biology, mathematics, physics, and computer sciences. Further, optimal control might be defined as the extension of static optimization, or even as some comments, the new face of Variational Calculus.
In this talk we present several examples from life sciences analyzed with the supp...
This paper proposes the simultaneous application of molecular dynamics, systems biology, biomechanics, and computational intelligence for a single aim: understanding numerically the vitreous detachment, an ophthalmologic disorder (pathophysiology). The paper is theoretical and seminar in some sense, letting for further papers the detailed labors. T...
EM TRABALHOS PASSADOS, O AUTOR TRABALHOU EM UM ALGORITMO SUPOSTAMENTE PARA SER APLICADO COM ESTRATÉGIA EVOLUTIVA. ESTE EVOLVEU A APLICAÇÃO DE ANÁLISE DE COMPONENTES PRINCIPAIS EM JUNÇÃO COM PRINCÍPIOS DA ESTRATÉGIA EVOLUTIVA. O CORRENTE TRABALHO OBJETIVA TRAZER O REFERIDO ESFORÇO CIENTÍFICO NOVAMENTE À DISCUSSÃO. A MOTIVAÇÃO ESTÁ NA CRESÇA DO AUTOR...
Em estudos recentes, observamos uma tendência atual em estudos bio-inspirados. De forma nem sempre destacada, essa onda de estudos é algo recente, mas com raízes no passado (alguns referem aos estudos de Aristóteles). Podemos afirmar com grau difícil de quantificar que essa onda estará entre os desafios do milênio com promessas de desenvolvimento d...
Abstract— on the current manuscript, we dissert on the application of Artificial Neural Network (ANN) as alternative and complementary approach for the observer-based method in transcription network; which is a recent proposed tool for modeling transcription networks. In view of that, it is claimed that neural networks as models for applied mathema...
On the current manuscript, we dissert on the application of Artificial Neural Network (ANN) as alternative and complementary approach for the observer-based method in transcription network, which is a recent proposed tool for modeling transcription networks. In view of that, it is claimed that neural networks as models for applied mathematics may s...
On this manuscript, we report the proposal of the use of computational intelligence methods as a powerful and valuable source of mathematical tools for modelling gene expression networks. Gene expression networks are modelled via transcription networks. Transcription networks are graph-oriented mathematical-computational models that attempt to unde...
Neural Networks have been applied widely to real problem modeling. The applications have
been concentrated mainly on image processing, classification of patterns, and function
approximation. The best characteristic of neural networks from the point of view for function
approximation is the parallel processing power. Besides neural networks by its o...
In this work we report the study and proposal of a new product, an accumulation sensor
of radiation dose for using on neonatal jaundice treatment, phototherapy. The working
principle of this device is based on the sensitivity of polymeric solution under blue
radiation. The polymeric device discussed here uses the phenomenon characterized by
the cha...
Neste trabalho é apresentado o estudo e a proposta de um novo produto, um sensor de acúmulo de dose de radiação para uso no monitoramento do tratamento da icterícia neonatal, a fototerapia. Esse possui princípio de funcionamento baseado na sensibilidade de soluções poliméricas eletrônicas ao serem expostas à radiação durante um intervalo, caracteri...
Neste trabalho é apresentado o estudo e a proposta de um novo produto, um sensor de acúmulo de dose de radiação para uso no monitoramento do tratamento da icterícia neonatal, a fototerapia. Esse possui princípio de funcionamento baseado na sensibilidade de soluções poliméricas eletrônicas ao serem expostas à radiação durante um intervalo, caracteri...
As Estratégias Evolutivas representam uma classe de métodos estocásticos de
otimização, que trabalham com uma população de soluções candidatas no domínio de
busca. Neste artigo, a matriz de covariância amostral da população é usada para
definir as mutações aplicadas aos indivíduos da população, de tal forma que as
direções e tamanhos de passo dessa...
As Estratégias Evolutivas representam uma classe de métodos estocásticos de otimização, que trabalham com uma população de soluções candidatas no domínio de busca. Neste estudo, a matriz de covariância amostral da população é usada para definir as mutações aplicadas aos indivíduos da população, de tal forma que as direções e tamanhos de passo dessa...
The present work details, to our knowledge, the first examination of the influence of blue-light radiation on the optical properties of organic luminescent films in attempting to develop an indicator dosimeter for phototherapy of neonatal jaundice. Jaundice is the most common problem encountered in newborns due to immature functioning in the liver....
Questions
Questions (16)
Please, let me know your thoughts on the peer review process
Preprint
Dear all, it is with great pleasure that I make public my latest exploration of openAI APIs. On this prototype, I have tested a medical chatbot.
Hope you enjoy the reading!
#bioinformatics #healthinformatics #medicine #chatbots #largelanguagemodels #openai #computervision #deeplearning #medicalimaging
You can leave a public review on
I am interested in collaborations
Semaglutide mimics the activity of a hormone naturally produced by humans in their intestines known as glucagon-like peptide 1 or, popularly, GLP-1. The release of this hormone in the body and consequent activation of GLP-1 receptors increases insulin release, causing a reduction in blood glucose levels, an important role in the treatment of diabetes.
This is a recent promise to handle obesity, and Science recognized as a big achievement on the fight against obesity.
During my PhD, I have created and worked with models focused on GLP-1, and on the guts.
#bioinformatics #biomathematics #obesity
Recently, I have received a nice review on my paper.
**Dependency on External APIs:** Relying on external APIs, such as OpenAI and iNaturalist, introduces a dependency on the availability and stability of these services. Any disruptions or changes in these APIs could impact the functionality of your system.
Let me know your thoughts on the matter
Learn more on: https://www.qeios.com/read/YS5U67
I have written a piece on the new release from openAI. It can analyze CSV flles, like a pro.
Could artificial intelligence now threaten data scientists? programmers are already dommed! 🤣
Read more: https://www.qeios.com/read/76QMHB
Recently, on my paper, I have by accident written something interesting:
"If we make an analogy to human: gpt-3.5-turbo-1106 [chatGPT] on this case specifically did not fall into confirmation bias." Source: https://www.qeios.com/read/Y13B20
Have you ever wondered on the place of biases in artificial intelligence? how much of the human biases will be passed to artificial intelligence?
Would AI be immunize from biases?
Dear all, please, join me discussing my latest preprint.
Feel free to leave a review as well.
Conversational Artificial Intelligence (CAI) was the latest big step towards artificial general intelligence (AGI): models of AI that are generic, that can solve problems without being restricted to a small set of problems they were designed for. OpenAI with chatGPT gave a big step towards this direction. On the other hand, being able to classify snakes from images can help the general public, and even experts to classify snakes (e.g., finding the right snake serum). There are more than 2.000 different species of snakes worldwide. On this paper, we explore the latest releases of openAI APIs. We integrate with a previous work we did, using transfer learning to classify snakes. We have used their GPT Vision API for describing uploaded images textually, their latest chatGPT API for deciding which model to use for classifying an image and also to generate a human-friendly final textual response. Additionally, we also tested their GPT 4 API instead of the chatGPT API as a comparison. We found that the integration was a success. By giving our models to openAI API, it decides which model to call as so it could give an educated guess to the user based on an uploaded image from the snake. The best result was when we used the GPT 4 API, something we already expected. We hope that this prototype can be scaled up with more species. We did a test of concept, and showed that the basics needed to build such a system for snake classification is possible with current technologies. We hope to contribute to sparking research that brings together computer scientists and biologists, generally called bioinformatics.
=
Join me on this discussion:
SnakeChat: a conversational-AI based app for snake classification
