Personal tools

Difference between revisions of "User:Spmatteo"

From iis-projects

Jump to: navigation, search
(Interests)
Line 2: Line 2:
  
 
== Matteo Spallanzani ==
 
== Matteo Spallanzani ==
 +
 
I received my PhD in applied mathematics in February 2020 from the University of Modena and Reggio Emilia (UniMoRe), Italy, with a thesis on "A framework for the analysis of machine learning systems".
 
I received my PhD in applied mathematics in February 2020 from the University of Modena and Reggio Emilia (UniMoRe), Italy, with a thesis on "A framework for the analysis of machine learning systems".
While at UniMoRe, I have contributed to create the machine learning division of the High-Performance Real-Time (HiPeRT) laboratory led by professor Marko Bertogna.
+
I have been working on data science and machine learning for five years, both in academia and industry (Tetra Pak, Maserati, Advertima).
I have been working on data science and machine learning for a while, fields in which I have also had some industrial experiences either as an intern or a scientific consultant (Tetra Pak, Maserati, Advertima).
+
 
  
 
== Interests ==
 
== Interests ==
Line 12: Line 13:
 
My research interests lie at the intersection of mathematical analysis, stochastic optimisation, algorithms, and parallel programming.
 
My research interests lie at the intersection of mathematical analysis, stochastic optimisation, algorithms, and parallel programming.
  
At IIS, I am working on quantized neural networks (QNNs), applying neural architecture search (NAS) to improve their function approximation properties, developing new algorithms to improve their learning process, and crafting tools to deploy them on resource-constrained computing platforms.
+
At IIS, I am working on quantised neural networks (QNNs): applying data science techniques to know how good networks look like, developing new algorithms to improve their learning process, and crafting tools to deploy them on resource-constrained computing platforms.
 +
 
  
 
== Contact Information ==
 
== Contact Information ==
 +
 
* '''Office''': ETZ J76.2
 
* '''Office''': ETZ J76.2
 
* '''telephone''': (+41 44 63) 384 70
 
* '''telephone''': (+41 44 63) 384 70
 
* '''e-mail''': [mailto:spmatteo@iis.ee.ethz.ch spmatteo@iis.ee.ethz.ch]
 
* '''e-mail''': [mailto:spmatteo@iis.ee.ethz.ch spmatteo@iis.ee.ethz.ch]
 
* '''www''': [https://ee.ethz.ch/the-department/people-a-z/person-detail.MjUxODcz.TGlzdC8zMjc5LC0xNjUwNTg5ODIw.html Matteo Spallanzani (ETH page)]
 
* '''www''': [https://ee.ethz.ch/the-department/people-a-z/person-detail.MjUxODcz.TGlzdC8zMjc5LC0xNjUwNTg5ODIw.html Matteo Spallanzani (ETH page)]
 +
  
 
== Available Projects ==
 
== Available Projects ==
 +
 
<DynamicPageList>
 
<DynamicPageList>
 
supresserrors = true
 
supresserrors = true
Line 27: Line 32:
 
</DynamicPageList>
 
</DynamicPageList>
  
 
+
[[Category:Supervisors]]
[[Category:Supervisors]] [[Category: Deep Learning Acceleration]] [[Category: Software]]
+
[[Category: Algorithm]]
 +
[[Category: Software]]
 +
[[Category: Deep Learning Acceleration]]

Revision as of 20:55, 24 September 2021

Matteo sp.JPG

Matteo Spallanzani

I received my PhD in applied mathematics in February 2020 from the University of Modena and Reggio Emilia (UniMoRe), Italy, with a thesis on "A framework for the analysis of machine learning systems". I have been working on data science and machine learning for five years, both in academia and industry (Tetra Pak, Maserati, Advertima).


Interests

I am interested in everything that can help me finding and understanding the patterns hidden in our world. Since I found out that boosting statistical models with parallel computers can be pretty efficient at this task, I have made it my job to understand how machine learning systems work and how to apply them to real-world problems. My research interests lie at the intersection of mathematical analysis, stochastic optimisation, algorithms, and parallel programming.

At IIS, I am working on quantised neural networks (QNNs): applying data science techniques to know how good networks look like, developing new algorithms to improve their learning process, and crafting tools to deploy them on resource-constrained computing platforms.


Contact Information


Available Projects

No pages meet these criteria.