Abstract
Artificial Intelligence (AI) combines computer science and robust datasets to mimic natural intelligence demonstrated by human beings to aid in problem-solving and decision-making involving consciousness up to a certain extent. From Apple’s virtual personal assistant, Siri, to Tesla’s self-driving cars, research and development in the field of AI is progressing rapidly along with privacy concerns surrounding the usage and storage of user data on external servers which has further fueled the need of modern ultra-efficient AI networks and algorithms. The scope of the work presented within this paper focuses on introducing a modern image classifier which is a light-weight and ultra-efficient CNN intended to be deployed on local embedded systems, also known as edge devices, for general-purpose usage. This work is an extension of the award-winning paper entitled ‘CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems’ published for the 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC). The proposed neural network dubbed CondenseNeXtV2 utilizes a new self-querying augmentation policy technique on the target dataset along with adaption to the latest version of PyTorch framework and activation functions resulting in improved efficiency in image classification computation and accuracy. Finally, we deploy the trained weights of CondenseNeXtV2 on NXP BlueBox which is an edge device designed to serve as a development platform for self-driving cars, and conclusions will be extrapolated accordingly.
Highlights
Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN), which is a subset of Machine Learning (ML), designed to realize and harness power of Artificial Intelligence (AI) to simulate natural intelligence demonstrated by living creatures of the Kingdom Animalia
The scope of the work presented within this paper focuses on introducing a modern image classifier named CondenseNeXtV2 which is light-weight and ultra-efficient that is intended to be deployed on local embedded systems, known as edge devices, for
The scope of the work presented within this paper focuses on introducing a modern image classifier named CondenseNeXtV2 which is light-weight and ultra-efficient that is intended to be deployed on local embedded systems, known as edge devices, for general-purpose usage
Summary
Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN), which is a subset of Machine Learning (ML), designed to realize and harness power of Artificial Intelligence (AI) to simulate natural intelligence demonstrated by living creatures of the Kingdom Animalia. Networks (ANN) take inspiration from the human brain. Networks brainArtificial is a complex non-linear processing system capable of retraining reorganiz Neuraland (ANN). A and human ing its structural components known neurons to perform operations brain is acrucial complex and non-linear processing systemas capable of retraining and complex reorganizing such as image classification object detection much complex faster than any general-purpose its crucial structural componentsand known as neurons to perform operations such as image classification and object detection faster than using any general-purpose computer computer in existence today. ANNs much are developed a common programming lan in existence today. ANNs developed a common programming trained guage, trained and thenare deployed onusing computer hardware capablelanguage, of executing objective and tasks deployed on computer hardwareon capable of executing objective-specific tasks or way by specific or deployed to simulate a computer. ANNs function in a similar way by: Extracting knowledge using neurons and, Storing the extracted information with the help of inter-neuron connection strengths
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
