In general, artificial intelligence (AI) is the ability of a computer system to correctly interpret external data, learn from such data, and use that knowledge to achieve specific tasks and goals. The basic idea of neural networks is to have a set of “neurons” connected to each other, working together, without a specific task for each one. The concept of having several computational units that become intelligent due to the interactions between them is inspired by the brain, but its application is purely mathematical: given several parameters there is a way to combine them to predict a certain result. At present we can provide these algorithms with the necessary resources to be able to adjust their parameters, or “learn”, given the enormous amount of data generated. Deep Learning allows the computer to build complex concepts from simple concepts, this benefits us when reality is very complex and we cannot resort to a defined mathematical model, so we choose to model it with AI. At LIAN it was used successfully for early recognition of pluripotent stem cell differentiation. Currently, we are faced with the challenge of differentiating a normal tissue from a neoplastic one by means of differential expression data of genes extracted from control and patient transcriptomes.
Notifications
Español
