These days, nearly all AI-based products in our lives rely on “deep neural networks” that automatically learn to process labeled data. For most organisations and individuals, though, deep learning is tough to break into. To learn well, neural networks normally have to be quite large and need massive datasets. This training process usually requires multiple…

The post MIT’s AI Plot Twist: Neural Nets Can Work Just As Well Even If They’re 10x Smaller appeared first on Analytics India Magazine.