LSTMs, Plus a Deep Learning History Lesson with Jürgen Schmidhuber - TWiML Talk #44
Published:Aug 28, 2017 22:43
•1 min read
•Practical AI
Analysis
This article highlights an interview with Jürgen Schmidhuber, a prominent figure in the AI field, discussing his work on Long Short-Term Memory (LSTM) networks and providing a historical overview of deep learning. The interview took place at IDSIA, Schmidhuber's lab in Switzerland. The article emphasizes the importance of LSTMs in recent deep learning advancements and promises an insightful discussion, likening the experience to a journey through AI history. The article also mentions Schmidhuber's role at NNaisense, a company focused on large-scale neural network solutions.
Key Takeaways
Reference
“We talked a bunch about his work on neural networks, especially LSTM’s, or Long Short-Term Memory networks, which are a key innovation behind many of the advances we’ve seen in deep learning and its application over the past few years.”