Artificial Intelligence (AI) is the ability of machines to simulate the intelligence capability of higher organisms. AI has established its prevalence in many fields like mathematics, physiology, computing, biology and psychology. Ideally, an AI system should respond logically, be self-aware, have the ability to learn from the experience, and be able to discern and respond to external environments. With Deep Learning and Machine Learning algorithms, intellect systems that can perform the activities requiring human intellect, can be developed.
Advancements of Artificial Intelligence (AI) in medical and biological sciences have opened new ways for drug development. Novel therapeutic molecules and their target action can be easily predicted and can be modified. AI helps in disease detection and diagnosis faster. The breakthrough of AI is made especially in the area of personalized precision medicine, host-pathogen interaction and predictive epidemiology. These approaches could help in faster decision-making with minimal errors that can improve risk analysis, especially disease diagnosis and selecting treatment strategy. In agricultural practices, an exact combination of fertilizers, pesticides, herbicides, soil management, water requirement analysis, yield prediction and overall crop management can be modified by implementing AI interventions. AI could provide a better improvement in agriculture, medical research, pharmaceuticals and bio-based industries for a sustainable life.
The interaction between Artificial Intelligence (AI) and human cognition in the digital age has made it possible for machines to carry out tasks that were previously limited to human intellect. Unlike conventional algorithms which are deterministic, rule-based operations, it is a highly disruptive technological breakthrough that comprises two main subsets namely, Machine Learning (ML) and Deep Learning (DL). Machine Learning is a subfield of Artificial Intelligence that, as quoted by Arthur Samuel, gives “computers the ability to learn without being explicitly programmed.”. It primarily deals with the exploration of data and the construction of algorithms that can learn from the data and make predictions based on it and is also closely associated and overlaps with the domain of computational statistics. ML algorithms do not follow strict static program instructions and can make data-driven predictions or decisions, by creating models from sample inputs. ML models are usually unsupervised or supervised; the former is essentially a system that learns by itself by identification of patterns in data, it establishes baseline behavior of various entities in data and finds meaningful anomalies within it whereas the latter is trained with labeled subsets of data and learns by comparing new unlabeled input with the known labeled data that it is trained on using methods like classification, regression, gradient boosting and prediction.
Deep Learning, also referred to as hierarchical learning, is an advanced machine learning concept based on artificial neural networks (ANNs). It is an approach within ML that focuses on learning complex representations directly from data. It primarily deals with the study of ANNs and related algorithms which contain more than one hidden layer. These methods use a cascade of layers of nonlinear processing units for feature extraction and transformation. Each layer takes the output from its preceding layer as input. The algorithms may be supervised or unsupervised. DL algorithms learn multiple levels of representations corresponding to different levels of abstraction, thus forming a hierarchical representation of concepts.
The key features of this book are: AI in medical Sciences, biotechnology and drug discovery; Application of AI in Digital Pathology, cytology and bioinformatics; Overview of AI, Machine Learning and Deep Learning; Impact of Artificial Intelligence in Society; Artificial Intelligence in Pharmacovigilance; and Ethics in Artificial Intelligence. The volume aims to comprehensively cover the application of AI in biological sciences. It is a collection of contributions from different authors who have several years of experience in their specific areas. The book will be useful for pharma companies, CROs, product developers, students, researchers, academicians, policymakers and practitioners.
Скачать Artificial Intelligence and Biological Sciences
Навигация
Вход на сайт
Реклама
Artificial Intelligence and Biological Sciences 
