Chart Pattern Recognition using Markovian Models, talk by Yann Soullard (Friday 15 Jan, 11am)
by Announcements of talks＠IDSIA
Dear All,
Yann Soullard, from the Heudiasyc Lab of the University of Compiègne
will give a talk on "Chart Pattern Recognition using Markovian
Models" this Friday, the 15th, at 11am in IDSIA’s meeting room
(Galleria 1 bldg in Manno). Please find the abstract here below.
Abstract.
A chart pattern is a particular shape which appears in financial stock
markets. It is defined by theoretical rules and it has a predictive
power. Detecting such patterns is difficult. There is an important gap
between theory and practice; real patterns do not perfectly respect
the theoretical rules. Moreover, the definition of chart patterns
seems subjective; it depends on the financial expert. Finally, there
are no large labeled datasets of chart patterns. We investigate chart
pattern recognition using statistical Markovian systems. We focused on
generative (Hidden Markov Models) and discriminative (Hidden
Conditional Random Fields) approaches which are standard technologies
for sequential data recognition. We proposed various strategies to
learn accurate systems with small labeled training sets. The first one
blends HMMs and HCRFs in such a way that the modeling ability of the
generative models is used to limit the overfitting of the
discriminative ones. The second strategy is a semi-supervised approach
which combines an HMM and an HCRF system during the learning step.
This second approach has some similarity with a co-training algorithm.
Best regards,
Alessandro
_________________________________
Alessandro Antonucci
IDSIA
Dalle Molle Institute
for Artificial Intelligence
Via Cantonale (Galleria 2)
CH-6928, Manno-Lugano, CH
mail: alessandro(a)idsia.ch
skype: alessandro.antonucci
tel: +41 916108515
web: www.idsia.ch/~alessandro
_________________________________
8 years, 11 months
- 1
- 1
Web Liquid Streams - Masiar Babazadeh - Monday 11 Jan - 11h00
by Announcements of talks＠IDSIA
Dear All,
Maser Babazadeh will give us a talk on the streaming framework Web Liquid Streams,
on Monday the 11th at 11h00 in IDSIA’s meeting room (Galleria 1 bldg in Manno).
Abstract
Thanks to the recent introduction of peer-to-peer communication between browsers with WebRTC, real time processing of streams can now be deployed on browsers in addition to traditional server-side execution environments. In this talk we present the Web Liquid Streams framework for building and executing stream processing topologies capable of gathering data from Web-enabled sensors and process it through JavaScript operators scattered across a peer-to-peer Cloud of computing peers. WLS offers i) support for arbitrary topologies and data streams, ii) deployment on heterogeneous Web-enabled devices, iii) transparent stream delivery across the WebRTC, WebSockets and ZeroMQ protocols, iv) stateful and stateless operators. WLS takes care of the deployment of the topology on the available resources, while users are only required to implement the operators and describe the topology graph using JSON. The structure of the topology can be dynamically adapted without stopping the stream flowing through it. The talk will present the platform and its programming interface, showing a preliminary evaluation of the system.
Masar is a PhD candidate at the Faculty of Informatics at Università della Svizzera Italiana.
Best regards
Andrea
8 years, 11 months
- 1
- 0
- ← Newer
- 1
- Older →