Nikhil Buduma A Deep Dive into Recurrent Neural Nets

Last time, we talked about the traditional feed-forward neural net and concepts that form the basis of deep learning. These ideas are extremely powerful! We saw how feed-forward convolutional neural networks have set records on many difficult tasks including handwritten digit recognition and object classification. And even today, feed-forward neural networks consistently outperform virtually all other approaches to solving classification tasks. And yet, despite their well celebrated successes, most experts would agree that feed-forward neural nets are still rather limited in what they can achieve.