首页|New Findings in Computational Intelligence Described from University of Tokyo (D evelopment and Practical Applications of Computational Intelligence Technology)
New Findings in Computational Intelligence Described from University of Tokyo (D evelopment and Practical Applications of Computational Intelligence Technology)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on computational intellig ence is the subject of a new report. According to news originating from Tokyo, J apan, by NewsRx correspondents, research stated, "Computational intelligence (CI ) uses applied computational methods for problem-solving inspired by the behavio r of humans and animals. Biological systems are used to construct software to so lve complex problems, and one type of such system is an artificial immune system (AIS), which imitates the immune system of a living body." Our news correspondents obtained a quote from the research from University of To kyo: "AISs have been used to solve problems that require identification and lear ning, such as computer virus identification and removal, image identification, a nd function optimization problems. In the body's immune system, a wide variety o f cells work together to distinguish between the self and non-self and to elimin ate the non-self. AISs enable learning and discrimination by imitating part or a ll of the mechanisms of a living body's immune system. Certainly, some deep neur al networks have exceptional performance that far surpasses that of humans in ce rtain tasks, but to build such a network, a huge amount of data is first require d. These networks are used in a wide range of applications, such as extracting k nowledge from a large amount of data, learning from past actions, and creating t he optimal solution (the optimization problem). A new technique for pre-training natural language processing (NLP) software ver.9.1by using transformers called Bidirectional Encoder Representations (BERT) builds on recent research in pre-tr aining contextual representations, including Semi-Supervised Sequence Learning, Generative Pre-Training, ELMo (Embeddings from Language Models), which is a meth od for obtaining distributed representations that consider context, and ULMFit ( Universal Language Model Fine-Tuning). BERT is a method that can address the iss ue of the need for large amounts of data, which is inherent in large-scale model s, by using pre-learning with unlabeled data. An optimization problem involves " finding a solution that maximizes or minimizes an objective function under given constraints". In recent years, machine learning approaches that consider patter n recognition as an optimization problem have become popular. This pattern recog nition is an operation that associates patterns observed as spatial and temporal changes in signals with classes to which they belong."
University of TokyoTokyoJapanAsiaComputational IntelligenceCybersecurityEmerging TechnologiesMachine Learn ingSoftwareTechnology
NETL
NSTL
