William Vorhies's Blog Posts Tagged 'LSTM' (4)

The Coming Revolution in Recurrent Neural Nets (RNNs)

Summary: Recurrent Neural Nets (RNNs) are at the core of the most common AI applications in use today but we are rapidly recognizing broad time series problem types where they don’t fit well. Several alternatives are already in use and one that’s just been introduced, ODE net is a radical departure from our way of thinking about the solution.

…

Continue

Added by William Vorhies on March 11, 2019 at 7:30am — No Comments

Combining CNNs and RNNs – Crazy or Genius?

Summary: There are some interesting use cases where combining CNNs and RNN/LSTMs seems to make sense and a number of researchers pursuing this. However, the latest trends in CNNs may make this obsolete.

There are things that just don’t seem to go together. Take oil and water for instance. Both valuable, but try putting…

Continue

Added by William Vorhies on August 14, 2018 at 7:34am — 3 Comments

Temporal Convolutional Nets (TCNs) Take Over from RNNs for NLP Predictions

Summary: Our starting assumption that sequence problems (language, speech, and others) are the natural domain of RNNs is being challenged. Temporal Convolutional Nets (TCNs) which are our workhorse CNNs with a few new features are outperforming RNNs on major applications today. Looks like RNNs may well be history.

…

Continue

Added by William Vorhies on May 1, 2018 at 7:29am — 1 Comment

Automated Deep Learning – So Simple Anyone Can Do It

Summary: There are several things holding back our use of deep learning methods and chief among them is that they are complicated and hard. Now there are three platforms that offer Automated Deep Learning (ADL) so simple that almost anyone can do it.

There are several things holding back our use of deep learning methods…