Even Faster CNNs: Exploring the New Class of Winograd Algorithms

Presented by

Gian Marco Iodice, Staff Software Engineer

About this talk

Over the past decade, deep learning networks have revolutionized the task of classification and recognition in a broad area of applications. Recent developments have shown how these workloads can be implemented on low-power, Arm-based platforms. During this webinar, you will gain an insight into: • The recently introduced class of algorithms that can reduce the arithmetic complexity of convolution layers with small filter sizes • The latest optimizations techniques for the most common solutions, such as GEMM • The design of Winograd algorithms, with an analysis of the complexity and the performance achieved for convolutional neural networks

Related topics:

More from this channel

Upcoming talks (1)
On-demand talks (98)
Subscribers (16753)
From providing the IP for the chip to delivering the cloud services that allow organizations to securely manage the deployment of products throughout their lifecycle, Arm delivers a complete Internet of Things (IoT) solution for our partners and customers. It’s rooted in our deep understanding of the future of compute and security.