#podcast #T2E13 The artificial intelligence revolution would not have been possible without the adaptation of libraries for computation on graphics cards, also known as GPUs. GPUs made it possible to reduce training time by several orders of magnitude, allowing much more complex and accurate models to be created. Today’s AI requires many of these and […]
#podcast #T2E12 Programming… Recombining… Did you know that you can make programs that program? In this episode we talk about Genetic Programming, a special type of bio-inspired algorithm capable of evolving trees, a special type of graph where there is only one way to go from one vertex to another. Our guest, José María Luna […]
#podcast #T2E11 There are concepts, people, data that are connected and interact with each other, in a network that explains much of the world around us. And in mathematics – and in computer science – all these interactions can be modeled as a graph. A graph is a structure that combines two types of objects: […]
#podcast #T2E10 Dear biologists, we have plagiarized you!! First it was Charles Darwin in his famous book “The Origin of Species“, where he talks about genetics (the science that studies how certain traits and characteristics are transmitted from parents to offspring), natural selection and survival of the fittest. Then it was John Holland, years later, […]
#podcast #T2E9 Data. Always data. Data is all around us, and there is a lot of talk about personal data, profiles, etc. But there is a special type that is not so well known: sequences. Data ordered according to a specific criterion; for example, this text. It is ordered according to the grammatical rules of […]
#podcast #T2E8 Artificial Intelligence does not live by neural networks alone. There are numerous algorithms beyond that, and many of them are also inspired by nature. In this episode we discuss one of the best-known bio-inspired algorithms: the ant colony algorithm, which has countless uses, from finding the shortest paths on google maps to optimizing […]
#podcast #T2E7 Many of us are familiar with forensic science thanks to series such as CSI or Bones. The protagonists of these series are very fluent in describing characteristics of human remains, such as population, sex, age, etc., or even identify a crime victim without DNA evidence. But in real life, these tasks are very […]
#podcast #T2E6 In November 2021, OpenAI finally opened the GPT-3 API to everyone. GPT-3 is a neural network for natural language processing that meant a breakthrough in the quality of generated text, and that attracted strong attention from mainstream media at the end of 2020. In this episode we bring attention to the mechanism underlying […]
#podcast #T2E5 Continuing our series on neural networks, this time it is the turn of convolutional neural networks. Responsible for the great popularity of deep learning in recent years, convolutional networks have drastically changed how we design systems for images. In this episode we talk about convolutions, primary classes and COVID with our colleague Anabel […]
#podcast #T2E4 Data privacy is one of the most important challenges facing artificial intelligence. To build models, it is often necessary to have access to all the data, and in the case of particularly sensitive data, it involves numerous ethical issues. Federated learning was born to offer a viable alternative: building large-scale models using many […]
#podcast #T2E3 The first neural networks emerged in the 50’s. At first they consisted of very few neurons, and long training processes, but they already gave very relevant results in very varied fields such as astronomy or chemistry. Today we talk about the percpetron, the multilayer perceptron, and its applications in various fields with Sebastián […]
#podcast #T2E2 The study of data is fundamental to any science. Statistics and processing algorithms play a fundamental role for fields like Astronomy and Astrophysics, where observations are noisy. But at the same time, they allow us to calculate orbits to detect planets light years away from our planet. We will talk about astronomy and […]
#podcast #T2E9 Already at the dawn of artificial intelligence, scientists looked to nature. And specifically, the human brain, the paradigm of “natural” intelligence. So the logical thing to do was to be inspired, and create analogues of neurons and their connections. In this way, back in the 1950s, the foundations of neural networks as we […]