1 / 18

COSC 460 – Neural Networks

COSC 460 – Neural Networks. Gregory Caza 17 August 2007. Elman (1993). Elman, J. L. (1993). Learning and development in neural networks: the importance of starting small. Cognition 48: 71-99. Modelling first language acquisition using a progressive training strategy. Elman (1993).

stamos
Download Presentation

COSC 460 – Neural Networks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. COSC 460 – Neural Networks Gregory Caza 17 August 2007

  2. Elman (1993) • Elman, J. L. (1993). Learning and development in neural networks: the importance of starting small. Cognition 48: 71-99. • Modelling first language acquisition using a progressive training strategy.

  3. Elman (1993) • Simple Recurrent Network (SRN) • context units remember the state of the hidden units at the last time step

  4. Elman (1993) • input was a binary-encoded word • words are presented one at a time • output was an encoded prediction of the next word in a sentence • predictions are expected to depend on the network learning a grammatical structure

  5. Elman (1993) • developmental constraints may facilitate learning • limited view provides a buffer from a complex, potentially overwhelming domain • simple network = child • complex domain = language

  6. Elman (1993) • Training was performed using three different schemata: • using all training data and a fully-developed network • with the training data organized and presented with increasing complexity • beginning with a limited memory that increased throughout training

  7. Elman (1993) • developmental simulation #1: incremental input • training sentences were classified as simple or complex • ratio of complex : simple increased over time

  8. Elman (1993) • developmental simulation #2: incremental memory • context would be reset when memory limit was reached

  9. Elman (1993) • full set: learning did not successfully complete • incremental input: low final error; good generalization • incremental memory: low final error; good generalization

  10. Elman (1993) • can training with a subset construct a “foundation for future success”? • filter out “stimuli which may either be irrelevant or require prior learning to be interpreted” • solution space is constrained

  11. Elman (1993) • Questions • how many sentences/epochs were used in the failed case? • what were the quantitative differences between the incremental memory/input results? • were results reproducible with different training corpora?

  12. Assad et al. (2002) • Assad, C., Harmann, M. J., Paulin, M. G. (2002). Control of a simulated arm using a novel combination of cerebellar learning mechanisms. Neurocomputing 44-46: 275-283. • Control of a robot arm using dynamic state estimation.

  13. Assad et al. (2002) • explore the cerebellum’s role in dynamic state estimation during movement • single-link robot arm, capable of single-plane movement and releasing a ball • ANN used to control the release time of the throw, with the goal of hitting a target at a certain height

  14. Assad et al. (2002) • 6 Purkinje cells (PC) • 6 climbing fibres (CF) • 6 ascending branches (AB) • 4280 parallel fibres (PF) - 600 inhibitory; 3680 excitatory

  15. Assad et al. (2002) • each excitatory PF received a radial basis function (RBF) of 2 state variables • PF-PC connections were strengthened through ‘Hebbian-like’ learning • after each trial, a binary error signal was generated based on throw accuracy • if the ball hit the target window, PF-PC connections were strengthened through ‘Hebbian-like’ learning

  16. Assad et al. (2002) • the target window was initialized to be “quite large” • if a hit was recorded, the window was shrunk • if there was an error, the window was expanded

  17. Assad et al. (2002) • physiological experiments demonstrate LTD between PF and CF • most cerebellar models ignore the AB input • the network suggests a possible role for LTP in cerebellar learning through the AB

  18. Assad et al. (2002) • details, details! • too complicated => laying groundwork for experiments • Why does no learning take place when the target is missed? What about negative reinforcement?

More Related