Winograd Convolution: A Perspective from Fault Tolerance

Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation. Other than the computing efficiency, we observe its great potential in improving NN fault tolerance and evaluate its fault tolerance comprehensively for the first time. Then, we explore the use of fault tolerance of winograd convolution for either fault-tolerant or energy-efficient NN processing. According to our experiments, winograd convolution can be utilized to reduce fault-tolerant design overhead by 27.49\% or energy consumption by 7.19\% without any accuracy loss compared to that without being aware of the fault tolerance

Optimizing Deep Neural Networks via Discretization of Finite-Time Convergent Flows

In this paper, we investigate in the context of deep neural networks, the performance of several discretization algorithms for two first-order finite-time optimization flows. These flows are, namely, the rescaled-gradient flow (RGF) and the signed-gradient flow (SGF), and consist of non-Lipscthiz or discontinuous dynamical systems that converge locally in finite time to the minima of gradient-dominated functions. We introduce three discretization methods for these first-order finite-time flows, and provide convergence guarantees. We then apply the proposed algorithms in training neural networks and empirically test their performances on three standard datasets, namely, CIFAR10, SVHN, and MNIST. Our results show that our schemes demonstrate faster convergences against standard optimization alternatives, while achieving equivalent or better accuracy.

Analysis and Adaptation of YOLOv4 for Object Detection in Aerial Images

The recent and rapid growth in Unmanned Aerial Vehicles (UAVs) deployment for various computer vision tasks has paved the path for numerous opportunities to make them more effective and valuable. Object detection in aerial images is challenging due to variations in appearance, pose, and scale. Autonomous aerial flight systems with their inherited limited memory and computational power demand accurate and computationally efficient detection algorithms for real-time applications. Our work shows the adaptation of the popular YOLOv4 framework for predicting the objects and their locations in aerial images with high accuracy and inference speed. We utilized transfer learning for faster convergence of the model on the VisDrone DET aerial object detection dataset. The trained model resulted in a mean average precision (mAP) of 45.64% with an inference speed reaching 8.7 FPS on the Tesla K80 GPU and was highly accurate in detecting truncated and occluded objects. We experimentally evaluated the impact of varying network resolution sizes and training epochs on the performance. A comparative study with several contemporary aerial object detectors proved that YOLOv4 performed better, implying a more suitable detection algorithm to incorporate on aerial platforms.

Kernel Packet: An Exact and Scalable Algorithm for Gaussian Process Regression with Matérn Correlations

We develop an exact and scalable algorithm for one-dimensional Gaussian process regression with Mat\'ern correlations whose smoothness parameter $\nu$ is a half-integer. The proposed algorithm only requires $\mathcal{O}(\nu^3 n)$ operations and $\mathcal{O}(\nu n)$ storage. This leads to a linear-cost solver since $\nu$ is chosen to be fixed and usually very small in most applications. The proposed method can be applied to multi-dimensional problems if a full grid or a sparse grid design is used. The proposed method is based on a novel theory for Mat\'ern correlation functions. We find that a suitable rearrangement of these correlation functions can produce a compactly supported function, called a "kernel packet". Using a set of kernel packets as basis functions leads to a sparse representation of the covariance matrix that results in the proposed algorithm. Simulation studies show that the proposed algorithm, when applicable, is significantly superior to the existing alternatives in both the computational time and predictive accuracy.

Towards On-Board Panoptic Segmentation of Multispectral Satellite Images

With tremendous advancements in low-power embedded computing devices and remote sensing instruments, the traditional satellite image processing pipeline which includes an expensive data transfer step prior to processing data on the ground is being replaced by on-board processing of captured data. This paradigm shift enables critical and time-sensitive analytic intelligence to be acquired in a timely manner on-board the satellite itself. However, at present, the on-board processing of multi-spectral satellite images is limited to classification and segmentation tasks. Extending this processing to its next logical level, in this paper we propose a lightweight pipeline for on-board panoptic segmentation of multi-spectral satellite images. Panoptic segmentation offers major economic and environmental insights, ranging from yield estimation from agricultural lands to intelligence for complex military applications. Nevertheless, the on-board intelligence extraction raises several challenges due to the loss of temporal observations and the need to generate predictions from a single image sample. To address this challenge, we propose a multimodal teacher network based on a cross-modality attention-based fusion strategy to improve the segmentation accuracy by exploiting data from multiple modes. We also propose an online knowledge distillation framework to transfer the knowledge learned by this multi-modal teacher network to a uni-modal student which receives only a single frame input, and is more appropriate for an on-board environment. We benchmark our approach against existing state-of-the-art panoptic segmentation models using the PASTIS multi-spectral panoptic segmentation dataset considering an on-board processing setting. Our evaluations demonstrate a substantial increase in accuracy metrics compared to the existing state-of-the-art models.

Pulses with Minimum Residual Intersymbol Interference for Faster than Nyquist Signaling

Faster than Nyquist signaling increases the spectral efficiency of pulse amplitude modulation by accepting intersymbol interference, where an equalizer is needed at the receiver. Since the complexity of an optimal equalizer increases exponentially with the number of the interfering symbols, practical truncated equalizers assume shorter memory. The power of the resulting residual interference depends on the transmit filter and limits the performance of truncated equalizers. In this paper, we use numerical optimizations and the prolate spheroidal wave functions to find optimal time-limited pulses that achieve minimum residual interference. Compared to root raised cosine pulses, the new pulses decrease the residual interference by an order of magnitude, for example, a decrease by 32 dB is achieved for an equalizer that considers four interfering symbols at 57% faster transmissions. As a proof of concept, for the 57% faster transmissions of binary symbols, we showed that using the new pulse with a 4-state equalizer has better bit error rate performance compared to using a root raised cosine pulse with a 128-state equalizer.

NU HLT at CMCL 2022 Shared Task: Multilingual and Crosslingual Prediction of Human Reading Behavior in Universal Language Space

In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words are transformed to their universal language representation via the International Phonetic Alphabet (IPA). To the best of our knowledge, this is the first study to favorable exploit this phonological property of language for the two tasks. Various feature types were extracted covering basic frequencies, n-grams, information theoretic, and psycholinguistically-motivated predictors for model training. A finetuned Random Forest model obtained best performance for both tasks with 3.8031 and 3.9065 MAE scores for mean first fixation duration (FFDAvg) and mean total reading time (TRTAvg) respectively.

How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures

The unprecedented performance of deep neural networks (DNNs) has led to large strides in various Artificial Intelligence (AI) inference tasks, such as object and speech recognition. Nevertheless, deploying such AI models across commodity devices faces significant challenges: large computational cost, multiple performance objectives, hardware heterogeneity and a common need for high accuracy, together pose critical problems to the deployment of DNNs across the various embedded and mobile devices in the wild. As such, we have yet to witness the mainstream usage of state-of-the-art deep learning algorithms across consumer devices. In this paper, we provide preliminary answers to this potentially game-changing question by presenting an array of design techniques for efficient AI systems. We start by examining the major roadblocks when targeting both programmable processors and custom accelerators. Then, we present diverse methods for achieving real-time performance following a cross-stack approach. These span model-, system- and hardware-level techniques, and their combination. Our findings provide illustrative examples of AI systems that do not overburden mobile hardware, while also indicating how they can improve inference accuracy. Moreover, we showcase how custom ASIC- and FPGA-based accelerators can be an enabling factor for next-generation AI applications, such as multi-DNN systems. Collectively, these results highlight the critical need for further exploration as to how the various cross-stack solutions can be best combined in order to bring the latest advances in deep learning close to users, in a robust and efficient manner.

A Computational Architecture for Machine Consciousness and Artificial Superintelligence: Updating Working Memory Iteratively

This theoretical article examines how to construct human-like working memory and thought processes within a computer. There should be two working memory stores, one analogous to sustained firing in association cortex, and one analogous to synaptic potentiation in the cerebral cortex. These stores must be constantly updated with new representations that arise from either environmental stimulation or internal processing. They should be updated continuously, and in an iterative fashion, meaning that, in the next state, some items in the set of coactive items should always be retained. Thus, the set of concepts coactive in working memory will evolve gradually and incrementally over time. This makes each state is a revised iteration of the preceding state and causes successive states to overlap and blend with respect to the set of representations they contain. As new representations are added and old ones are subtracted, some remain active for several seconds over the course of these changes. This persistent activity, similar to that used in artificial recurrent neural networks, is used to spread activation energy throughout the global workspace to search for the next associative update. The result is a chain of associatively linked intermediate states that are capable of advancing toward a solution or goal. Iterative updating is conceptualized here as an information processing strategy, a computational and neurophysiological determinant of the stream of thought, and an algorithm for designing and programming artificial intelligence.

Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis

The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence. The development of the ABSA task is very much hindered by the lack of annotated data. To tackle this, the prior works have studied the possibility of utilizing the sentiment analysis (SA) datasets to assist in training the ABSA model, primarily via pretraining or multi-task learning. In this article, we follow this line, and for the first time, we manage to apply the Pseudo-Label (PL) method to merge the two homogeneous tasks. While it seems straightforward to use generated pseudo labels to handle this case of label granularity unification for two highly related tasks, we identify its major challenge in this paper and propose a novel framework, dubbed as Dual-granularity Pseudo Labeling (DPL). Further, similar to PL, we regard the DPL as a general framework capable of combining other prior methods in the literature. Through extensive experiments, DPL has achieved state-of-the-art performance on standard benchmarks surpassing the prior work significantly.