{"componentChunkName":"component---src-templates-blog-post-js","path":"/blog/theres-more-to-machine-learning-than-cnns/","result":{"data":{"site":{"siteMetadata":{"title":"No Frills News"}},"contentfulNfnPost":{"postTitle":"There’s More To Machine Learning Than CNNs","slug":"theres-more-to-machine-learning-than-cnns","createdLocal":"2021-06-09 14:30:51.182511","publishDate":"2021-06-09 07:01:22+00:00","feedName":"Image Recognition","sourceUrl":{"sourceUrl":"https://semiengineering.com/theres-more-to-machine-learning-than-cnns/"},"postSummary":{"childMarkdownRemark":{"html":"<p>Neural networks – and convolutional neural networks (CNNs) in particular – have received an abundance of attention over the last few years, but they’re not the only useful machine-learning structures.\n“Neural networks can do all this really complex pattern recognition stuff, especially the convolutional neural networks,” said Elias Fallon, software engineering group director, custom IC &#x26; PCB group at Cadence.\nConventional neural networksArtificial neural networks (ANNs), the most familiar structures, deepen the original perceptron idea.\nConvolutional neural networks (CNNs) arguably have the most dedicated hardware solutions.\nThe difference is that in the older case, the decisions were specifically created by the developer, while the machine learns the heuristics in a decision tree.</p>"}}}},"pageContext":{"slug":"theres-more-to-machine-learning-than-cnns"}}}