More Like this

1. Soft Error Resilient Deep Learning Systems Using Neuron Gradient Statistics

   https://doi.org/10.1109/IOLTS56730.2022.9897815  

   Amarnath, Chandramouli; Mejri, Mohamed; Ma, Kwondo; Chatterjee, Abhijit (September 2022, International On-Line Testing Symposium)

   Deep learning techniques have been widely adopted in daily life with applications ranging from face recognition to recommender systems. The substantial overhead of conventional error tolerance techniques precludes their widespread use, while approaches involving median filtering and invariant generation rely on alterations to DNN training that may be difficult to achieve for larger networks on larger datasets. To address this issue, this paper presents a novel approach taking advantage of the statistics of neuron output gradients to identify and suppress erroneous neuron values. By using the statistics of neurons’ gradients with respect to their neighbors, tighter statistical thresholds are obtained compared to the use of neuron output values alone. This approach is modular and is combined with accurate, low-overhead error detection methods to ensure it is used only when needed, further reducing its cost. Deep learning models can be trained using standard methods and our error correction module is fit to a trained DNN, achieving comparable or superior performance compared to baseline error correction methods while incurring comparable hardware overhead without needing to modify DNN training or utilize specialized hardware architectures. 

   more » « less
2. A Novel Approach to Error Resilience in Online Reinforcement Learning

   Chandramouli, Amarnath.; Chatterjee, Abhijit. (July 2023, International On-Line Testing Symposium)

   Online reinforcement learning (RL) based systems are being increasingly deployed in a variety of safety-critical applications ranging from drone control to medical robotics. These systems typically use RL onboard rather than relying on remote operation from high-performance datacenters. Due to the dynamic nature of the environments they work in, onboard RL hardware is vulnerable to soft errors from radiation, thermal effects and electrical noise that corrupt the results of computations. Existing approaches to on-line error resilience in machine learning systems have relied on availability of the large training datasets to configure resilience parameters, which is not necessarily feasible for online RL systems. Similarly, other approaches involving specialized hardware or modifications to training algorithms are difficult to implement for onboard RL applications. In contrast, we present a novel error resilience approach for online RL that makes use of running statistics collected across the (real-time) RL training process to configure error detection thresholds without the need to access a reference training dataset. In this methodology, statistical concentration bounds leveraging running statistics are used to diagnose neuron outputs as erroneous. These erroneous neurons are then set to zero (suppressed). Our approach is compared against the state of the art and validated on several RL algorithms involving the use of multiple concentration bounds on CPU as well as GPU hardware. 

   more » « less
3. Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

   Ahmed, Shibbir; Gao, Hongyang; Rajan, Hridesh (April 2024, Association for Computing Machinery)

   Deep learning models are trained with certain assumptions about the data during the development stage and then used for prediction in the deployment stage. It is important to reason about the trustworthiness of the model's predictions with unseen data during deployment. Existing methods for specifying and verifying traditional software are insufficient for this task, as they cannot handle the complexity of DNN model architecture and expected outcomes. In this work, we propose a novel technique that uses rules derived from neural network computations to infer data preconditions for a DNN model to determine the trustworthiness of its predictions. Our approach, DeepInfer involves introducing a novel abstraction for a trained DNN model that enables weakest precondition reasoning using Dijkstra's Predicate Transformer Semantics. By deriving rules over the inductive type of neural network abstract representation, we can overcome the matrix dimensionality issues that arise from the backward non-linear computation from the output layer to the input layer. We utilize the weakest precondition computation using rules of each kind of activation function to compute layer-wise precondition from the given postcondition on the final output of a deep neural network. We extensively evaluated DeepInfer on 29 real-world DNN models using four different datasets collected from five different sources and demonstrated the utility, effectiveness, and performance improvement over closely related work. DeepInfer efficiently detects correct and incorrect predictions of high-accuracy models with high recall (0.98) and high F-1 score (0.84) and has significantly improved over the prior technique, SelfChecker. The average runtime overhead of DeepInfer is low, 0.22 sec for all the unseen datasets. We also compared runtime overhead using the same hardware settings and found that DeepInfer is 3.27 times faster than SelfChecker, the state-of- the-art in this area. 

   more » « less
4. DeepLocalize: Fault Localization for Deep Neural Networks

   https://doi.org/10.1109/ICSE43902.2021.00034  

   Wardat, Mohammad; Le, Wei; Rajan, Hridesh (May 2021, 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE))

   null (Ed.)

   Deep Neural Networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques don't support localizing DNN bugs because of the lack of understanding of model behaviors. The entire DNN model appears as a black box. To address these problems, we propose an approach and a tool that automatically determines whether the model is buggy or not, and identifies the root causes for DNN errors. Our key insight is that historic trends in values propagated between layers can be analyzed to identify faults, and also localize faults. To that end, we first enable dynamic analysis of deep learning applications: by converting it into an imperative representation and alternatively using a callback mechanism. Both mechanisms allows us to insert probes that enable dynamic analysis over the traces produced by the DNN while it is being trained on the training data. We then conduct dynamic analysis over the traces to identify the faulty layer or hyperparameter that causes the error. We propose an algorithm for identifying root causes by capturing any numerical error and monitoring the model during training and finding the relevance of every layer/parameter on the DNN outcome. We have collected a benchmark containing 40 buggy models and patches that contain real errors in deep learning applications from Stack Overflow and GitHub. Our benchmark can be used to evaluate automated debugging tools and repair techniques. We have evaluated our approach using this DNN bug-and-patch benchmark, and the results showed that our approach is much more effective than the existing debugging approach used in the state-of-the-practice Keras library. For 34/40 cases, our approach was able to detect faults whereas the best debugging approach provided by Keras detected 32/40 faults. Our approach was able to localize 21/40 bugs whereas Keras did not localize any faults. 

   more » « less
5. NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace

   https://doi.org/10.1002/aisy.202300841  

   Poduval, Prathyush P; Ni, Yang; Zou, Zhuowen; Ni, Kai; Imani, Mohsen (July 2024, Advanced Intelligent Systems)

   The 6G network, the next‐generation communication system, is envisaged to provide unprecedented experience through hyperconnectivity involving everything. The communication should hold artificial intelligence‐centric network infrastructures as interconnecting a swarm of machines. However, existing network systems use orthogonal modulation and costly error correction code; they are very sensitive to noise and rely on many processing layers. These schemes impose significant overhead on low‐power internet of things devices connected to noisy networks. Herein, a hyperdimensional network‐based system, called , is proposed, which enables robust and efficient data communication/learning. exploits a redundant and holographic representation of hyperdimensional computing (HDC) to design highly robust data modulation, enabling two functionalities on transmitted data: 1) an iterative decoding method that translates the vector back to the original data without error correction mechanisms, or 2) a native hyperdimensional learning technique on transmitted data with no need for costly data decoding. A hardware accelerator that supports both data decoding and hyperdimensional learning using a unified accelerator is also developed. The evaluation shows that provides a bit error rate comparable to that of state‐of‐the‐art modulation schemes while achieving 9.4 faster and 27.8 higher energy efficiency compared to state‐of‐the‐art deep learning systems. 

   more » « less