More Like this

1. Differentiable MPC for End-to-end Planning and Control

   Amos, B.; Rodriguez, I.; Sacks, J.; Boots, B.; Kolter, Z. (January 2018, Advances in neural information processing systems)
2. End-to-End Optimization and Learning for Multiagent Ensembles

   Kotary, James; Di Vito, Vincenzo; Fioretto, Ferdinando (November 2022, arXivorg)
3. Efficient and Robust LiDAR-Based End-to-End Navigation

   Zhijian Liu*, Alexander Amini* (May 2021, IEEE International Conference on Robotics and Automation (ICRA))

   null (Ed.)
4. Cascaded Projection: End-to-End Network Compression and Acceleration

   Minnehan, Breton; Savakis, Andreas (June 2019, IEEE Conference on Computer Vision and Pattern Recognition)

   We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of the features that requires more memory, or select only a subset of features by pruning entire filter channels. We propose the Cascaded Projection (CaP) compression method that projects the output and input filter channels of successive layers to a unified low dimensional space based on a low-rank projection. We optimize the projection to minimize classification loss and the difference between the next layer’s features in the compressed and uncompressed networks. To solve this non-convex optimization problem we propose a new optimization method of a proxy matrix using back propagation and Stochastic Gradient Descent (SGD) with geometric constraints. Our cascaded projection approach leads to improvements in all critical areas of network compression: high accuracy, low memory consumption, low parameter count and high processing speed. The proposed CaP method demonstrates state-of-the-art results compressing VGG16 and ResNet networks with over 4× reduction in the number of computations and excellent performance in top-5 accuracy on the ImageNet dataset before and after fine-tuning. 

   more » « less
5. End-to-End Image Classification and Compression with variational autoencoders

   https://doi.org/10.1109/JIOT.2022.3182313  

   Chamain, Lahiru D.; Qi, Siyu; Ding, Zhi (August 2022, IEEE Internet of Things Journal)

   The past decade has witnessed the rising dominance of deep learning and artificial intelligence in a wide range of applications. In particular, the ocean of wireless smartphones and IoT devices continue to fuel the tremendous growth of edge/cloudbased machine learning (ML) systems including image/speech recognition and classification. To overcome the infrastructural barrier of limited network bandwidth in cloud ML, existing solutions have mainly relied on traditional compression codecs such as JPEG that were historically engineered for humanend users instead of ML algorithms. Traditional codecs do not necessarily preserve features important to ML algorithms under limited bandwidth, leading to potentially inferior performance. This work investigates application-driven optimization of programmable commercial codec settings for networked learning tasks such as image classification. Based on the foundation of variational autoencoders (VAEs), we develop an end-to-end networked learning framework by jointly optimizing the codec and classifier without reconstructing images for given data rate (bandwidth). Compared with standard JPEG codec, the proposed VAE joint compression and classification framework achieves classification accuracy improvement by over 10% and 4%, respectively, for CIFAR-10 and ImageNet-1k data sets at data rate of 0.8 bpp. Our proposed VAE-based models show 65%􀀀99% reductions in encoder size,  1.5􀀀 13.1 improvements in inference speed and 25%􀀀99% savings in power compared to baseline models. We further show that a simple decoder can reconstruct images with sufficient quality without compromising classification accuracy. 

   more » « less