摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报告的主题。根据NewsRx记者在英国牛津发布的新闻报道，研究表明：“合成药物化学在药物发现中起着至关重要的作用。今天有人工智能工具来指导下一步的合成，但许多是‘黑匣子’(BB)。”新闻记者从牛津大学的研究中引用了一句话：“除了所做的预测，没有人能学到什么。现在也有人工智能方法来表征可见性和‘可解释性’（即可解释的人工智能或XAI），当使用‘组成数据’时，这些方法会有所帮助。”如果概率方法与BB方法互补使用，并显示出具有可比性的预测能力，那么概率方法的预测能力就会大大提高，但它们往往从看似任意的学习权出发，缺乏从一开始就基于观察和计数的熟悉概率度量。他们将提供关于在下一次综合中应包括和避免哪些组的指导方针，并用概率术语量化关系。这些点通过对两种主要类型的BB方法和一种新的概率论“玻璃盒”(GB)方法的盲测试比较来证明，但这种方法似乎很适合上述情况。因为可能涉及许多概率，重点在于它最简单的解释模型的预测能力.通常有m个数量级的矿石非活性化合物,这通常是机器学习方法的一个问题.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Oxford, United Kingdom, by NewsRx journalists, research stated, "The synthetic medicinal chemi st plays a vital role in drug discovery. Today there are AI tools to guide next syntheses, but many are ‘Black Boxes' (BB)." The news reporters obtained a quote from the research from Oxford University, "O ne learns little more than the prediction made. There are now also AI methods em phasizing visibility and ‘explainability' (thus explainable AI or XAI) that coul d help when ‘compositional data' are used, but they often still start from seemi ngly arbitrary learned weights and lack familiar probabilistic measures based on observation and counting from the outset. If probabilistic methods were used in a complementary way with BB methods and demonstrated comparable predictive powe r, they would provide guidelines about what groups to include and avoid in next syntheses and quantify the relationships in probabilistic terms. These points ar e demonstrated by blind test comparison of two main types of BB methods and a pr obabilistic ‘Glass Box' (GB) method new outside of medicine, but which appears w ell suited to the above. Because many probabilities can be involved, emphasis is on the predictive power of its simplest explanatory models. There are usually m ore inactive compounds by orders of magnitude, often a problem for machine learn ing methods."
NETL
NSTL