Genuino 101
Presented by:
Federico Mascoma
Introduction
Introduction
Genuino 101
Curie
• Low Power Module
• 32 bit dual core with CK = 32Mhz
• Support MachineLearning Library
• Contains Real-Time Operating Systems (RTOS)
How to program the board?
Install the IDE from:
https://www.arduino.cc/en/Main/Software
How to program the board?
Open the IDE and
Select Arduino/Genuino 101
How to program the board?
Let IDE to help you!
PME
• The Pattern Matching Engine (PME) is a parallel data recognition
engine
• Two Classification Functions:
• k-nearest neighbors (KNN)
• Radial Basis Function (RBF)
• Classification states:
• ID - Identified , UNC - Uncertain , UNK - Unknown
• #include "CuriePME.h” is the Library that provide its API
Project
https://github.com/Mascoma95/Genuino101
Takes a pattern ”vector” of size ”vectorNumBytes”, and commits it to the
network as training data.
The ”letter-upperStart” parameter indicates to the PME which category
this training vector belongs to.
If a future input has a sufficiently similar pattern, it will be classified as
the same category passed with this pattern.
Takes a pattern ”vector” of
size ”vectorNumBytes”, and uses the
committed neurons in the network to
classify the pattern
Parameters
vector is a pointer to the data to be
classified. Pattern data must be no
longer than 128 bytes
vectorNumBytes is the size of the data
to be classified
Thanks

Genuino101presentation

  • 1.
  • 2.
  • 3.
  • 20.
    Curie • Low PowerModule • 32 bit dual core with CK = 32Mhz • Support MachineLearning Library • Contains Real-Time Operating Systems (RTOS)
  • 21.
    How to programthe board? Install the IDE from: https://www.arduino.cc/en/Main/Software
  • 22.
    How to programthe board? Open the IDE and Select Arduino/Genuino 101
  • 23.
    How to programthe board? Let IDE to help you!
  • 24.
    PME • The PatternMatching Engine (PME) is a parallel data recognition engine • Two Classification Functions: • k-nearest neighbors (KNN) • Radial Basis Function (RBF) • Classification states: • ID - Identified , UNC - Uncertain , UNK - Unknown • #include "CuriePME.h” is the Library that provide its API
  • 25.
  • 26.
    Takes a pattern”vector” of size ”vectorNumBytes”, and commits it to the network as training data. The ”letter-upperStart” parameter indicates to the PME which category this training vector belongs to. If a future input has a sufficiently similar pattern, it will be classified as the same category passed with this pattern.
  • 27.
    Takes a pattern”vector” of size ”vectorNumBytes”, and uses the committed neurons in the network to classify the pattern Parameters vector is a pointer to the data to be classified. Pattern data must be no longer than 128 bytes vectorNumBytes is the size of the data to be classified
  • 28.