By Giorgio Valentini, Francesco Masulli (auth.), Maria Marinaro, Roberto Tagliaferri (eds.)
This booklet constitutes the completely refereed post-proceedings of the thirteenth Italian Workshop on Neural Nets, WIRN VIETRI 2002, held in Vietri sul Mare, Italy in May/June 2002.
The 21 revised complete papers awarded including 3 invited papers have been conscientiously reviewed and revised in the course of rounds of choice and development. The papers are equipped in topical sections on architectures and algorithms, snapshot and sign processing purposes, and studying in neural networks.
Read Online or Download Neural Nets: 13th Italian Workshop on Neural Nets, WIRN VIETRI 2002 Vietri sul Mare, Italy, May 30 – June 1, 2002 Revised Papers PDF
Similar italian books
This publication includes a number of the papers offered on the symposium on "Decision techniques in Economics" which was once held in Modena (Italy) on 9-10 October 1989. It coincided with the yearly assembly of the italian crew on online game idea; the gang is shaped via economists, mathematicians, engineers and social scientists.
Alcuni pensano che il nostro cervello sia fermo all'età della pietra, come se los angeles selezione naturale ci avesse plasmato nel Pleistocene e poi abbandonato al nostro destino. Sui mass media spopolano i riferimenti all'evoluzione biologica dei comportamenti umani, soprattutto politici e sessuali. Dire che l'evoluzione ci ha programmati fin dal Paleolitico in line with avere un determinato impulso innato è una tentazione irresistibile, che ci fa raccontare un sacco di storie fantasiose e zeppe di stereotipi.
- L'uomo. La sua natura e il suo posto nel mondo
- Trattato marxista di economia Volume 2
- A cena con gli amici. Secondi di carne e di pesce
- Lettere a Lucilio (Italian Edition)
- Ahi serva Italia. Un appello ai miei concittadini
Additional info for Neural Nets: 13th Italian Workshop on Neural Nets, WIRN VIETRI 2002 Vietri sul Mare, Italy, May 30 – June 1, 2002 Revised Papers
Biz Abstract. For building an automatic trading system one needs: a significant variable for characterizing the ﬁnancial asset behaviours; a suitable algorithm for ﬁnding out the information hidden in such a variable; and a proper Trading Strategy for transforming these information in operative indications. Starting from recent results proposed in literature, we have conjectured that the Technical Analysis approach could reasonably extract the information present in prices and volumes. Like tool able to ﬁnd out the relation existing between the Technical Analysis inputs and an output we properly deﬁned, we use the Group Method of Data Handling, a soft-computing approach which gives back a polynomial approximation of the unknown relationship between the inputs and the output.
It is important to notice that the key principles of SLT, namely the idea that a trade oﬀ must be found between the complexity of a model and the error of a model on the existing training data, is a general one although it has been developed mainly having classiﬁcation and regression in mind. Therefore in general one should be able to develop models from data for any other problem as long as the following are deﬁned: 1. The type of the possible models is deﬁned, that is a “hypothesis space” is decided.
At ﬁrst, there are four variables linked to the time: x1 = date; x2 = month; x3 = hour (measured by number of bars; one bar is a period of 30 minutes); and x4 = day of the week. The ﬁrst one gives only a chronological reference, the others three are used as cyclical indicators. Then, the variables directly linked to the prices are: x5 = Ct , the close price of the last contract in the period that end at time t; x15 = Ht , the higher price the contract reaches in the period from t − 1 to t; x16 = Lt , the lower price the contract reaches in the period from t − 1 to t.