[robotics-worldwide] [meetings] Workshop on Deep Learning for Self-Driving Cars at ICRoM 2017
a.norouzzadeh at ee.kntu.ac.ir
Thu Oct 12 06:31:30 PDT 2017
We invite you to participate in our workshop on Deep Learning for Self-Driving Cars at ICRoM 2017, Oct 24th.
Deep learning, and in particular convolutional neural networks, has become the main component of many intelligent vehicle algorithms. Self-Driving Cars need to choose actions, e.g. steering commands which will affect the driving scenes encountered. This setting is well-suited to apply deep learning to determine the optimal commands. Recent advances in deep learning techniques in computer vision applied to a broad range of applications including classification, detection, and segmentation.
These techniques are used in self-driving cars in order to detect objects from camera images such as other cars, bicycles, pedestrians and etc. In camera-based sensing systems for intelligent vehicles, object detection offers the fundamental ability to real-time environment perception. In this workshop we explain what is deep learning and introduce open source software like Python, Keras and Tensorflow to build deep learning models on real world data. The workshop is conceived to maximize the learning experience for everyone and includes 50% theory and 50% hands-on practice. Previous experience programming in Python or in other languages is advised to make best use of the workshop. Additionally, some familiarity with machine learning is necessary.
The goal of this workshop is to bring together researchers and practitioners in the field of autonomous driving to address core challenges with machine learning. These contents of this workshop include, but are not limited to
1 - Introduction to Deep Neural Networks
2 - Finding lane lines by low-level image processing techniques
3 - Introduction to TensorFlow
4 - Traffic sign classification by TensorFlow
5 - Introduction to Keras
6 - Behavioral cloning
7 - Accurate and efficient vehicle detection
Hamid D. Taghirad (website : https://urldefense.proofpoint.com/v2/url?u=http-3A__aras.kntu.ac.ir_taghirad_&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=-tPRoFkV3bh3tTy8G0mrON9DHGHusO6ne-5FKSCso7U&s=BTg6dz_Hp0vPmj_h9nTm2IWLJROaAtYUj_ebmyfDcWc&e=)
Alireza Norouzzadeh Ravari : (website: https://urldefense.proofpoint.com/v2/url?u=http-3A__aras.kntu.ac.ir_anorouzzadeh_&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=-tPRoFkV3bh3tTy8G0mrON9DHGHusO6ne-5FKSCso7U&s=keEuGOzxESbd9lDJfmhHjkzsRj5AHZ-WJj-ntgH_DWU&e=)
Hamid D. Taghirad, Alireza Norouzzadeh Ravari
This message has been scanned by KNTU Antispam System (E.F.A. Project) and is believed to be clean.
More information about the robotics-worldwide