TY - GEN
T1 - Validation of machine learning algorithms through visualization methods
AU - Gallitz, Oliver
AU - Botsch, Michael
AU - De Candido, Oliver
AU - Utschick, Wolfgang
N1 - Publisher Copyright:
© 2018, VDI Verlag GMBH. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Machine Learning (ML) algonthms have recently become one ol the most important fields of industrial development efforts. Many companies in the automotive sector see ML methods as an enabler of autonomous driving, due to the promising capabilities of trained ML algorithms to represent complex structures and behavioral models. Consequently, the introduction of ML methods in industrial and safety related applications comes with the requirement of Verification & Validation (V&V) of ML algorithms. In order to validate a trained ML model, one not only needs to be able to interpret its outputs, but also the processes within the model itself. One option is to map the high-dimensional data onto lower-dimensional representations to alow users to interpret and understand the data ML algorithms use, e.g. by applying multi-dimensional scaling or t-distributed Stochastic Neighbor Embedding (t-SNE). Further methods that have led to a recent breakthrough in ML visualization require engineering knowledge to validate trie network activations throughout trie network. These methods help to gain insights into the fundamental features which the network learns. In the field of image processing these are mainly based on convolutional methods, such as Convolutional Neural Networks (CNNs) or Convolutional Auto-Encoders (CAEs). in this paper, we present these visualization techniques to establish, to a certain extent, the inlerpretability of ML methods, which in turn supports the validation of the algorithms. We also introduce possible approaches to tackle the problem of V&V for ML algorithms in the automotive sector, which are currently considered black box systems. Our paper attempts to provide an intuition of how validation might be achieved, and on the next steps researchers could take.
AB - Machine Learning (ML) algonthms have recently become one ol the most important fields of industrial development efforts. Many companies in the automotive sector see ML methods as an enabler of autonomous driving, due to the promising capabilities of trained ML algorithms to represent complex structures and behavioral models. Consequently, the introduction of ML methods in industrial and safety related applications comes with the requirement of Verification & Validation (V&V) of ML algorithms. In order to validate a trained ML model, one not only needs to be able to interpret its outputs, but also the processes within the model itself. One option is to map the high-dimensional data onto lower-dimensional representations to alow users to interpret and understand the data ML algorithms use, e.g. by applying multi-dimensional scaling or t-distributed Stochastic Neighbor Embedding (t-SNE). Further methods that have led to a recent breakthrough in ML visualization require engineering knowledge to validate trie network activations throughout trie network. These methods help to gain insights into the fundamental features which the network learns. In the field of image processing these are mainly based on convolutional methods, such as Convolutional Neural Networks (CNNs) or Convolutional Auto-Encoders (CAEs). in this paper, we present these visualization techniques to establish, to a certain extent, the inlerpretability of ML methods, which in turn supports the validation of the algorithms. We also introduce possible approaches to tackle the problem of V&V for ML algorithms in the automotive sector, which are currently considered black box systems. Our paper attempts to provide an intuition of how validation might be achieved, and on the next steps researchers could take.
UR - http://www.scopus.com/inward/record.url?scp=85106058314&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85106058314
SN - 9783180923178
SN - 9783180923185
SN - 9783180923208
SN - 9783180923215
SN - 9783180923222
SN - 9783180923239
SN - 9783180923246
SN - 9783180923253
SN - 9783180923260
SN - 9783180923277
SN - 9783180923284
SN - 9783180923291
SN - 9783180923307
SN - 9783180923314
SN - 9783180923321
SN - 9783180923338
SN - 9783180923345
SN - 9783180923352
SN - 9783180923369
SN - 9783180923376
SN - 9783180923383
T3 - VDI Berichte
SP - 29
EP - 46
BT - VDI Berichte
PB - VDI Verlag GMBH
T2 - 8th International VDI Congress on passenger car, commercial vehicle and off-highway applications, Market Place, 2018
Y2 - 16 October 2018 through 17 October 2018
ER -