Professor Russell’s book starts out with an entertaining journey through the history of AI and automation, as well as cautionary thinking about them. This discussion is well informed – he is a renown AI academic and co-author of a comprehensive and widely used AI textbook. Having provided historical background, the remainder of the book argues … Continue reading “Review: Human Compatible: Artificial Intelligence and the Problem of Control by Stuart Russell”
Common sense makes humans very efficient learners, so machine learning researchers have been working on ways to imbue machines with at least some ‘common sense’. In a previous blog we discussed using pictures to train natural language processing systems, in a sense giving the systems partial ‘knowledge’ of what words represent in the physical world. ML systems … Continue reading “Learning Common Sense from Video”
Natural language processing (NLP) machines have made great progress by learning to recognize complex statistical patterns in sentences and paragraphs. Work with modern deep learning models such as the transformer has shown that sufficiently large networks (hundreds of millions parameters) can do a good job processing language (e.g., translation), without having any information about what … Continue reading “Learning Words with Pictures”
‘If I have seen further, it is by standing on the shoulders of giants’ Sir Isaak Newton, 1619 Technical disciplines have always progressed by researchers building on past work, but the deep learning research community does this in spades with transfer learning. Transfer learning builds new deep learning systems on top of previously developed ones. … Continue reading “Machines Learning From Machines”
Training a Machine Learning system requires a journey through the cost terrain, where each location in the terrain represents particular values for all ML system parameters, and the height of the terrain is the cost, a mathematical value that reflects how well the ML system is performing for that parameter set (smaller cost means better … Continue reading “Navigating the Cost Terrain with Minibatches”
Machine learning applications generally rely on supervised learning, learning from training samples that have been labeled by a human ‘teacher’. Unsupervised learning learns what it can from unlabeled training samples. What can be learned this way are basic structural characteristics of the training data, and this information can be a useful aid to supervised learning. In my latest … Continue reading “Learning Without a Teacher”
Language is a hallmark of human intelligence, and Natural Language Processing (NLP) has long been a goal of Artificial Intelligence. The ability of early computers to process rules and look up definitions made machine translation seem right around the corner. However language proved to be more complicated than rules and definitions. The observation that humans … Continue reading “The Road to Human-Level Natural Language Processing”
iMerit is a remarkable company of over 4000 people that specializes in annotating the data needed to train machine learning systems. I am writing a series of blogs for them on various aspects of machine learning. In my latest blog I explain how ML systems embody both human intelligence and a form of machine ‘intelligence’. Just as … Continue reading “Encoding Human and Machine Knowledge for Machine Learning”
iMerit is a remarkable company of over 4000 people that specializes in annotating the data needed to train machine learning systems. I am writing a series of blogs for them on various aspects of machine learning. In my latest blog I explain how ML systems can be fooled by being either too ‘simple‘, too ‘inexperienced‘, or faced … Continue reading “The Three Edge Case Culprits: Bias, Variance, and Unpredictability”
iMerit is a remarkable company of over 4000 people that specializes in annotating the data needed to train machine learning systems. I am writing a series of blogs for them on various aspects of machine learning. In my latest blog I explain how inaccuracies in training data labels (‘label noise’) affect ML system performance. It turns … Continue reading “How Does Mislabeled Training Data Affect ML System Performance?”
Something went wrong. Please refresh the page and/or try again.
Follow My Blog
Get new content delivered directly to your inbox.