Efficiency Optimization of Trainable Feature Extractors for a Consumer Platform
نویسندگان
چکیده
This paper proposes an algorithmic optimization for the feature extractors of biologically inspired Convolutional Neural Networks (CNNs). CNNs are successfully used for different visual pattern recognition applications such as OCR, face detection and object classification. These applications require complex networks exceeding 100,000 interconnected computational nodes. To reduce the computational complexity a modified algorithm is proposed; real benchmarks show 65 83% reduction, with equal or even better recognition accuracy. Exploiting the available parallelism in CNNs is essential to reduce the computational scaling problems. Therefore the modified version of the algorithm is implemented and evaluated on a GPU platform to demonstrate the suitability on a cost effective parallel platform. A speedup of 2.5x with respect to the standard algorithm is achieved.
منابع مشابه
The MASH Project
It has been demonstrated repeatedly that combining multiple types of image features improves the performance of learning-based classification and regression. However, no tools exist to facilitate the creation of large pools of feature extractors by extended teams of contributors. The MASH project aims at creating such tools. It is organized around the development of a collaborative web platform...
متن کاملLearning audio and image representations with bio-inspired trainable feature extractors
Recent advancements in pattern recognition and signal processing concern the automatic learning of data representations from labeled training samples. Typical approaches are based on deep learning and convolutional neural networks, which require large amount of labeled training samples. In this work, we propose novel feature extractors that can be used to learn the representation of single prot...
متن کاملA Novel Approach to Improve the Training Time of Convolutional Networks for Object Recognition
Convolutional neural network is a kind of multi-layered neural network which facilitates the feature extraction and input-output mapping together with a global learning algorithm. The built-in trainable feature extractor of convolutional networks makes it a good candidate for endto-end object recognition problem. In addition, the trainable feature extractor is adaptable to different problem dom...
متن کاملA Classification Method for E-mail Spam Using a Hybrid Approach for Feature Selection Optimization
Spam is an unwanted email that is harmful to communications around the world. Spam leads to a growing problem in a personal email, so it would be essential to detect it. Machine learning is very useful to solve this problem as it shows good results in order to learn all the requisite patterns for classification due to its adaptive existence. Nonetheless, in spam detection, there are a large num...
متن کاملImage features for visual teach-and-repeat navigation in changing environments
We present an evaluation of standard image features in the context of long-term visual teach-and-repeat navigation of mobile robots, where the environment exhibits significant changes in appearance caused by seasonal weather variations and daily illumination changes. We argue that for long-term autonomous navigation, the viewpoint-, scaleand rotationinvariance of the standard feature extractors...
متن کامل