Jürgen Schmidhuber is a computer scientist whose research includes learning architectures for recurrent neural networks. He coauthored the1997long short-term memory paper with Sepp Hochreiter and the2000adaptive-forgetting paper with Felix A. Gers and Fred Cummins. These are team contributions documented by the original bylines.[ref] [ref] [ref]
The1997architecture separates a persistent internal state from learned control of access to that state. A LSTM input gate controls new input, while a LSTM output gate controls how stored information influences output. This arrangement was designed to reduce the vanishing gradient problem that makes distant events difficult to associate during learning.[ref]
Long Short-Term Memory by Sepp Hochreiter and Jürgen Schmidhuber. Abstract; Sections3–4: constant error flow and multiplicative gates
An illustrative task presents a marked value early in a long stream, then asks for it after many irrelevant inputs. A network needs both a way to retain the relevant information and a way to protect it from later interference. The paper tested artificial long-delay tasks; success on those experiments is evidence about the architecture and learning procedure under specified conditions, not a guarantee of unlimited or error-free memory.
Jürgen Schmidhuber, photograph linked from his author homepage
. External photograph identified in the Photos list of Jürgen Schmidhuber homepage. Articles by others on the same topic
There are currently no matching articles.