000			02112nam a2200301Ia 4500
003			OSt
005			20251118124936.0
008			220909b |||||||| |||| 00| 0 eng d
020			_a9781848165908
040			_aCSL _beng _cCSL
041			_aeng
084			_aD65,8(B):(S:72) Q0 TC _qCSL
100			_aWhittle, Peter _eauthor _9852009
245		0	_aNeural Nets and Chaotic Carriers
250			_a2nd
260			_aLondon : _bI C P , _c2010 .
300			_axii,230p.
490			_aAdvances in computer science and engineering
500			_aAppendix 213-218p.; References 219-224p.; Index 225-230p.
520			_aNeural Nets and Chaotic Carriers develops rational principles for the design of associative memories, with a view to applying these principles to models with irregularly oscillatory operation so evident in biological neural systems, and necessitated by the meaninglessness of absolute signal levels.Design is based on the criterion that an associative memory must be able to cope with “fading data”, i.e., to form an inference from the data even as its memory of that data degrades. The resultant net shows striking biological parallels. When these principles are combined with the Freeman specification of a neural oscillator, some remarkable effects emerge. For example, the commonly-observed phenomenon of neuronal bursting appears, with gamma-range oscillation modulated by a low-frequency square-wave oscillation (the “escapement oscillation”). Bridging studies and new results of artificial and biological neural networks, the book has a strong research character. It is, on the other hand, accessible to non-specialists for its concise exposition on the basics.
650			_aArtificial neural networks. _9852010
650			_aAssociative and storage memories. _9852011
650			_aComputer engineering. _9852012
650			_aOsillatory operation. _9852013
650			_aComputer science. _9852014
942			_hD65,8(B):(S:72) Q0 TC _cREF _2CC _n0
999			_c8877 _d8877