0
Your cart

Your cart is empty

Browse All departments
  • All departments
Price
  • R500 - R1,000 (1)
  • R2,500 - R5,000 (3)
  • -
Status
Brand

Showing 1 - 4 of 4 matches in All departments

Connectionist Approaches to Language Learning (Paperback, Softcover reprint of the original 1st ed. 1991): David Touretzky Connectionist Approaches to Language Learning (Paperback, Softcover reprint of the original 1st ed. 1991)
David Touretzky
R2,924 Discovery Miles 29 240 Ships in 7 - 11 working days

arise automatically as a result of the recursive structure of the task and the continuous nature of the SRN's state space. Elman also introduces a new graphical technique for study ing network behavior based on principal components analysis. He shows that sentences with multiple levels of embedding produce state space trajectories with an intriguing self similar structure. The development and shape of a recurrent network's state space is the subject of Pollack's paper, the most provocative in this collection. Pollack looks more closely at a connectionist network as a continuous dynamical system. He describes a new type of machine learning phenomenon: induction by phase transition. He then shows that under certain conditions, the state space created by these machines can have a fractal or chaotic structure, with a potentially infinite number of states. This is graphically illustrated using a higher-order recurrent network trained to recognize various regular languages over binary strings. Finally, Pollack suggests that it might be possible to exploit the fractal dynamics of these systems to achieve a generative capacity beyond that of finite-state machines."

Connectionist Approaches to Language Learning (Hardcover, Reprinted from Machine Learning, Volume 7:2/3): David Touretzky Connectionist Approaches to Language Learning (Hardcover, Reprinted from Machine Learning, Volume 7:2/3)
David Touretzky
R3,774 Discovery Miles 37 740 Ships in 7 - 11 working days

arise automatically as a result of the recursive structure of the task and the continuous nature of the SRN's state space. Elman also introduces a new graphical technique for study ing network behavior based on principal components analysis. He shows that sentences with multiple levels of embedding produce state space trajectories with an intriguing self similar structure. The development and shape of a recurrent network's state space is the subject of Pollack's paper, the most provocative in this collection. Pollack looks more closely at a connectionist network as a continuous dynamical system. He describes a new type of machine learning phenomenon: induction by phase transition. He then shows that under certain conditions, the state space created by these machines can have a fractal or chaotic structure, with a potentially infinite number of states. This is graphically illustrated using a higher-order recurrent network trained to recognize various regular languages over binary strings. Finally, Pollack suggests that it might be possible to exploit the fractal dynamics of these systems to achieve a generative capacity beyond that of finite-state machines."

Proceedings of the 1993 Connectionist Models Summer School (Hardcover): Michael C. Mozer, Paul Smolensky, David S. Touretzky,... Proceedings of the 1993 Connectionist Models Summer School (Hardcover)
Michael C. Mozer, Paul Smolensky, David S. Touretzky, Jeffrey L. Elman, Andreas S. Weigend
R2,511 Discovery Miles 25 110 Out of stock

The result of the 1993 Connectionist Models Summer School, the papers in this volume exemplify the tremendous breadth and depth of research underway in the field of neural networks. Although the slant of the summer school has always leaned toward cognitive science and artificial intelligence, the diverse scientific backgrounds and research interests of accepted students and invited faculty reflect the broad spectrum of areas contributing to neural networks, including artificial intelligence, cognitive science, computer science, engineering, mathematics, neuroscience, and physics. Providing an accurate picture of the state of the art in this fast-moving field, the proceedings of this intense two-week program of lectures, workshops, and informal discussions contains timely and high-quality work by the best and the brightest in the neural networks field.

Common Lisp: A Gentle Introduction to Symbolic Computation (Paperback): Touretzky Common Lisp: A Gentle Introduction to Symbolic Computation (Paperback)
Touretzky
R689 R584 Discovery Miles 5 840 Save R105 (15%) Ships in 10 - 15 working days

Geared toward experienced programmers as well as those unfamiliar with LISP, this text offers reader-friendly explanations of the artificial intelligence program and debugging tools such as DESCRIBE, INSPECT, TRACE, and STEP.

Free Delivery
Pinterest Twitter Facebook Google+
You may like...
Springsteen On Broadway
Bruce Springsteen CD  (2)
R323 R166 Discovery Miles 1 660
Swiss Miele Vacuum Bags
R159 R141 Discovery Miles 1 410
Angelcare On-the-Go Dispenser
 (2)
R141 R113 Discovery Miles 1 130
Gloop Change-A-Roo (Red & Yellow)
R49 Discovery Miles 490
Crayola Supertips Washable Markers (Pack…
R154 Discovery Miles 1 540
Fine Living Booster Car Seat - Black
 (11)
R399 R299 Discovery Miles 2 990
Marvel's Spider-Man: Miles Morales
R1,299 R1,187 Discovery Miles 11 870
Skullcandy Sesh In-Ear Earphones…
R799 R656 Discovery Miles 6 560
Hoover Power 5 Filter Kit
R499 R474 Discovery Miles 4 740
JBL C100SI Headset In-ear Black
R149 R129 Discovery Miles 1 290

 

Partners