Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
94,843
result(s) for
"experts"
Sort by:
Become a real estate appraiser
\"Examines the necessary training to become and everyday work of a real estate appraiser\"-- Provided by publisher.
Book
Co-intelligence : living and working with AI
\"From Wharton professor and author of the popular One Useful Thing Substack newsletter Ethan Mollick comes the definitive playbook for working, learning, and living in the new age of AI. The release of generative AI--from LLMs like ChatGPT to image generators like DALL-E-marks a new era. We have invented technologies that boost our physical capabilities and others that automate complex tasks, but never, until now, have we created a technology that can boost our intelligence--with an impact on work and life that researchers project will be greater than that of steam power or the internet. Mollick urges us not to turn away from AI, and instead to invite AI tools to the table. He demonstrates how AI can amplify our own capacities, acting in roles from brainstorming partner to cowriter to tutor to coach, and assesses its surprising, positive impact on business and organizations. Marshalling original research from workers and teams who are leading the rest of us in embracing and leveraging AI, Mollick cuts through the hype to make a frank and eye-opening case for the real value of AI tools. Moreover, Mollick argues that the long-term impact of AI will be different from what we expect, advantaging English majors and art history experts more than coders, and impacting knowledge workers more than blue-collar workers. Co-Intelligence shows what it means for individuals and for society to think together with smart machines, and why it's imperative that we all master that skill. Co-Intelligence challenges us to utilize AI's power without losing our identity, learn from it without being misled, and harness its gifts to create a better human future. Thought-provoking, optimistic, and lucid, Co-Intelligence reveals the promise and power of generative AI\"-- Provided by publisher.
Book
Mixture of experts: a literature survey
Mixture of experts (ME) is one of the most popular and interesting combining methods, which has great potential to improve performance in machine learning. ME is established based on the divide-and-conquer principle in which the problem space is divided between a few neural network experts, supervised by a gating network. In earlier works on ME, different strategies were developed to divide the problem space between the experts. To survey and analyse these methods more clearly, we present a categorisation of the ME literature based on this difference. Various ME implementations were classified into two groups, according to the partitioning strategies used and both how and when the gating network is involved in the partitioning and combining procedures. In the first group, The conventional ME and the extensions of this method stochastically partition the problem space into a number of subspaces using a special employed error function, and experts become specialised in each subspace. In the second group, the problem space is explicitly partitioned by the clustering method before the experts' training process starts, and each expert is then assigned to one of these sub-spaces. Based on the implicit problem space partitioning using a tacit competitive process between the experts, we call the first group the mixture of implicitly localised experts (MILE), and the second group is called mixture of explicitly localised experts (MELE), as it uses pre-specified clusters. The properties of both groups are investigated in comparison with each other. Investigation of MILE versus MELE, discussing the advantages and disadvantages of each group, showed that the two approaches have complementary features. Moreover, the features of the ME method are compared with other popular combining methods, including boosting and negative correlation learning methods. As the investigated methods have complementary strengths and limitations, previous researches that attempted to combine their features in integrated approaches are reviewed and, moreover, some suggestions are proposed for future research directions.[PUBLICATION ABSTRACT]
Journal Article
Fuzzy expert systems and fuzzy reasoning
Coverage is accessible to practitioners and academic readers alike. * Features end-of-chapter problems with answers provided in an appendix. * Includes discussions of rule-based systems not available in any other book. * Includes problem sets and tutorial programs available on the Wiley ftp site.
eBook
