Matching Items (5)

158769-Thumbnail Image.png

Efficient and Online Deep Learning through Model Plasticity and Stability

Description

The rapid advancement of Deep Neural Networks (DNNs), computing, and sensing technology has enabled many new applications, such as the self-driving vehicle, the surveillance drone, and the robotic system. Compared

The rapid advancement of Deep Neural Networks (DNNs), computing, and sensing technology has enabled many new applications, such as the self-driving vehicle, the surveillance drone, and the robotic system. Compared to conventional edge devices (e.g. cell phone or smart home devices), these emerging devices are required to deal with much more complicated and dynamic situations in real-time with bounded computation resources. However, there are several challenges, including but not limited to efficiency, real-time adaptation, model stability, and automation of architecture design.

To tackle the challenges mentioned above, model plasticity and stability are leveraged to achieve efficient and online deep learning, especially in the scenario of learning streaming data at the edge:

First, a dynamic training scheme named Continuous Growth and Pruning (CGaP) is proposed to compress the DNNs through growing important parameters and pruning unimportant ones, achieving up to 98.1% reduction in the number of parameters.

Second, this dissertation presents Progressive Segmented Training (PST), which targets catastrophic forgetting problems in continual learning through importance sampling, model segmentation, and memory-assisted balancing. PST achieves state-of-the-art accuracy with 1.5X FLOPs reduction in the complete inference path.

Third, to facilitate online learning in real applications, acquisitive learning (AL) is further proposed to emphasize both knowledge inheritance and acquisition: the majority of the knowledge is first pre-trained in the inherited model and then adapted to acquire new knowledge. The inherited model's stability is monitored by noise injection and the landscape of the loss function, while the acquisition is realized by importance sampling and model segmentation. Compared to a conventional scheme, AL reduces accuracy drop by >10X on CIFAR-100 dataset, with 5X reduction in latency per training image and 150X reduction in training FLOPs.

Finally, this dissertation presents evolutionary neural architecture search in light of model stability (ENAS-S). ENAS-S uses a novel fitness score, which addresses not only the accuracy but also the model stability, to search for an optimal inherited model for the application of continual learning. ENAS-S outperforms hand-designed DNNs when learning from a data stream at the edge.

In summary, in this dissertation, several algorithms exploiting model plasticity and model stability are presented to improve the efficiency and accuracy of deep neural networks, especially for the scenario of continual learning.

Contributors

Agent

Created

Date Created
  • 2020

158679-Thumbnail Image.png

Experimental Evaluation of the Feasibility of Wearable Piezoelectric Energy Harvesting

Description

Technological advances in low power wearable electronics and energy optimization techniques

make motion energy harvesting a viable energy source. However, it has not been

widely adopted due to bulky energy harvester designs

Technological advances in low power wearable electronics and energy optimization techniques

make motion energy harvesting a viable energy source. However, it has not been

widely adopted due to bulky energy harvester designs that are uncomfortable to wear. This

work addresses this problem by analyzing the feasibility of powering low wearable power

devices using piezoelectric energy generated at the human knee. We start with a novel

mathematical model for estimating the power generated from human knee joint movements.

This thesis’s major contribution is to analyze the feasibility of human motion energy harvesting

and validating this analytical model using a commercially available piezoelectric

module. To this end, we implemented an experimental setup that replicates a human knee.

Then, we performed experiments at different excitation frequencies and amplitudes with

two commercially available Macro Fiber Composite (MFC) modules. These experimental

results are used to validate the analytical model and predict the energy harvested as a function

of the number of steps taken in a day. The model estimates that 13μWcan be generated

on an average while walking with a 4.8% modeling error. The obtained results show that

piezoelectricity is indeed a viable approach for powering low-power wearable devices.

Contributors

Agent

Created

Date Created
  • 2020

158606-Thumbnail Image.png

Security and Usability in Mobile and IoT Systems

Description

Mobile and Internet-of-Things (IoT) systems have been widely used in many aspects

of human’s life. These systems are storing and operating on more and more sensitive

data of users. Attackers may want

Mobile and Internet-of-Things (IoT) systems have been widely used in many aspects

of human’s life. These systems are storing and operating on more and more sensitive

data of users. Attackers may want to obtain the data to peek at users’ privacy or

pollute the data to cause system malfunction. In addition, these systems are not

user-friendly for some people such as children, senior citizens, and visually impaired

users. Therefore, it is of cardinal significance to improve both security and usability

of mobile and IoT systems. This report consists of four parts: one automatic locking

system for mobile devices, one systematic study of security issues in crowdsourced

indoor positioning systems, one usable indoor navigation system, and practical attacks

on home alarm IoT systems.

Chapter 1 overviews the challenges and existing solutions in these areas. Chapater

2 introduces a novel system ilock which can automatically and immediately lock the

mobile devices to prevent data theft. Chapter 3 proposes attacks and countermeasures

for crowdsourced indoor positioning systems. Chapter 4 presents a context-aware indoor

navigation system which is more user-friendly for visual impaired people. Chapter

5 investigates some novel attacks on commercial home alarm systems. Chapter 6

concludes the report and discuss the future work.

Contributors

Agent

Created

Date Created
  • 2020

158684-Thumbnail Image.png

Efficient and Secure Deep Learning Inference System: A Software and Hardware Co-design Perspective

Description

The advances of Deep Learning (DL) achieved recently have successfully demonstrated its great potential of surpassing or close to human-level performance across multiple domains. Consequently, there exists a rising demand

The advances of Deep Learning (DL) achieved recently have successfully demonstrated its great potential of surpassing or close to human-level performance across multiple domains. Consequently, there exists a rising demand to deploy state-of-the-art DL algorithms, e.g., Deep Neural Networks (DNN), in real-world applications to release labors from repetitive work. On the one hand, the impressive performance achieved by the DNN normally accompanies with the drawbacks of intensive memory and power usage due to enormous model size and high computation workload, which significantly hampers their deployment on the resource-limited cyber-physical systems or edge devices. Thus, the urgent demand for enhancing the inference efficiency of DNN has also great research interests across various communities. On the other hand, scientists and engineers still have insufficient knowledge about the principles of DNN which makes it mostly be treated as a black-box. Under such circumstance, DNN is like "the sword of Damocles" where its security or fault-tolerance capability is an essential concern which cannot be circumvented.

Motivated by the aforementioned concerns, this dissertation comprehensively investigates the emerging efficiency and security issues of DNNs, from both software and hardware design perspectives. From the efficiency perspective, as the foundation technique for efficient inference of target DNN, the model compression via quantization is elaborated. In order to maximize the inference performance boost, the deployment of quantized DNN on the revolutionary Computing-in-Memory based neural accelerator is presented in a cross-layer (device/circuit/system) fashion. From the security perspective, the well known adversarial attack is investigated spanning from its original input attack form (aka. Adversarial example generation) to its parameter attack variant.

Contributors

Agent

Created

Date Created
  • 2020

158799-Thumbnail Image.png

Visual Perception, Prediction and Understanding with Relations

Description

Rapid development of computer vision applications such as image recognition and object detection has been enabled by the emerging deep learning technologies. To improve the accuracy further, deeper and wider

Rapid development of computer vision applications such as image recognition and object detection has been enabled by the emerging deep learning technologies. To improve the accuracy further, deeper and wider neural networks with diverse architecture are proposed for better feature extraction. Though the performance boost is impressive, only marginal improvement can be achieved with significantly increased computational overhead. One solution is to compress the exploding-sized model by dropping less important weights or channels. This is an effective solution that has been well explored. However, by utilizing the rich relation information of the data, one can also improve the accuracy with reasonable overhead. This work makes progress toward efficient and accurate visual tasks including detection, prediction and understanding by using relations.
For object detection, a novel approach, Graph Assisted Reasoning (GAR), is proposed to utilize a heterogeneous graph to model object-object relations and object-scene relations. GAR fuses the features from neighboring object nodes as well as scene nodes. In this way, GAR produces better recognition than that produced from individual object nodes. Moreover, compared to previous approaches using Recurrent Neural Network (RNN), GAR's light-weight and low-coupling architecture further facilitate its integration into the object detection module.

For trajectories prediction, a novel approach, namely Diverse Attention RNN (DAT-RNN), is proposed to handle the diversity of trajectories and modeling of neighboring relations. DAT-RNN integrates both temporal and spatial relations to improve the prediction under various circumstances.

Last but not least, this work presents a novel relation implication-enhanced (RIE) approach that improves relation detection through relation direction and implication. With the relation implication, the SGG model is exposed to more ground truth information and thus mitigates the overfitting problem of the biased datasets. Moreover, the enhancement with relation implication is compatible with various context encoding schemes.

Comprehensive experiments on benchmarking datasets demonstrate the efficacy of the proposed approaches.

Contributors

Agent

Created

Date Created
  • 2020