![]() The team set up the experimental neural network in a novel way. Lipson and Chen speculated that neural networks might learn faster and better if the systems were "trained" to recognize objects, animals, for instance, by using the power of one of the world's most highly evolved sounds - the human voice uttering specific words. Because numbers are such an efficient way to digitize data, programmers rarely deviate from a numbers-driven process when they develop a neural network. In contrast, spoken human language is more tonal and analog, and, when captured in a digital file, non-binary. The language of binary numbers conveys information compactly and precisely. "To understand why this finding is significant," said Lipson, "it's useful to understand how neural networks are usually programmed, and why using the sound of the human voice is a radical experiment." The researchers discovered that a neural network whose "training labels" consisted of sound files reached higher levels of performance in identifying objects in images than another network that had been programmed in a more traditional manner that used simple binary inputs. ![]() National Science Foundation-funded study by mechanical engineer Hod Lipson and researcher Boyuan Chen proves that artificial intelligence systems might reach higher levels of performance if they are programmed with sound files of human language rather than with numerical data labels. ![]() According to new research from Columbia Engineering, that could be about to change.Ī new U.S. The notion that computers prefer to "speak" in binary numbers is rarely questioned. ![]() The digital revolution is built on a foundation of binaries, invisible 1s and 0s called bits. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |