Learning Sequential Tasks by Incrementally Adding Higher Orders

By Mark B. Ring. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Some of the GPUbased FNN implementations (Sections 5.16–5.19) have greatly contributed to recent successes in contests for pattern recognition (Sections 5.19–5.22), image segmentation (Section 5.21), and object detection (Sections 5.21–5.22).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, background): “This triggered work on partially observable Markov decision problems (POMDPs) [223, 222, 227, 204, 205, 206, 316, 148, 278, 122, 152, 25, 114, 160, 126, 308, 309, 183].”
Bridging Long Time Lags by Weight Guessing and \Long Short Term Memory" (1996, background): “…tasks, though, are more di(cid:14)cult than the above benchmark problems: they cannot be solved at all in reasonable time by random search (we tried various architectures) nor any other recurrent net learning algorithm we are aware of, e.g., [25, 20, 7, 8, 33, 14, 21, 5, 15, 29, 1, 24, 26, 19].”
Learning to Learn (1998, unknown): “In [Dayan and Hinton, 1993; Kaelbling, 1993; Lin, 1992; Ring, 1993; Ring, 1995; Singh, 1992; Thrun and Schwartz, 1995; Whitehead et aL, 1993], various reinforcement learning algorithms are described that basically can learn to learn via piecewise functional decomposition (although most of them have ”
Lifelong Machine Learning Systems: Beyond Learning Algorithms (2013, methodology): “In this way the learning system is initialized in favour of a particular region of hypothesis space of the modeling system (Ring 1993; Shavlik and Dietterich 1990; Singh 1992).”
A Clockwork RNN (2014, background): “Temporal Transition Hierarchy (TTH; Ring, 1993) incrementally adds high-order neurons in order to build a memory that is used to disambiguate an input at the current time step.”
A Connectionist Symbol Manipulator that Discovers the Structure of Context-Free Languages (1992, background): “The di cult problem of extracting multilevel structure from complex, extendedsequences has been studied by Mozer (1992), Ring (1993), Rohwer (1990), andSchmidhuber (1992), among others.”
Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies (2001, methodology): “Ring [21] also proposes a method for bridging long time lags.”
Long Short-Term Memory (1997, unknown): “4 Ring’s Approach. Ring (1993) also proposed a method for bridging long time lags.”