The goal of this blog is to create a Vitis 2021.1 hardware accelerator platform for the Zybo-Z7-20 board from Digilent. If you are interested to know how to use this platform to accelerate different compute-intensive tasks such as Support Vector Machine (SVM) on an FPGA-based embedded system, please refer to here. Before starting the process of creating a Vitis hardware platform, we should install two software tools. After installing the required software tools, we should prepare the folder hierarchy. Then customise it and enable five clocks in the output clocks tab.

As per the definition found in Britannica by Copeland, AI is commonly referred to as a computer system with human intellectual features, e.g., reasoning, discovering, generalizing, and learning from prior exposure [1,2]. U.S Food and Drug Administration (US-FDA) has also stated in 2019 that AI has the potential to transform the healthcare industry by its ability to derive new information from the vast dataset that feeds into it [2,3]. Machine learning (ML) can be simply understood as a subset of an application of AI in which machines analyze and use a large dataset to produce unique algorithms capable of "statistical learning" as described by Gutierrez [2]. The use of ML has surged in critical care in the field of the discovery of drugs, diagnostic tools, medical imaging, and therapeutics amongst others. It can potentially help us better understand the vast set of data available to us in an intensive care unit (ICU) and apply it to tackle a multitude of medical conditions [2,4]. ML can be divided into two main models based on learning tasks, which are supervised and unsupervised learning algorithms.

The past century has witnessed a massive increase in our ability to perform complex calculations. The development of the transistor in the 1950s, followed by the silicone integrated circuit, accelerated those capabilities and gave rise to what is commonly known as Moore's Law. According to this principle, the number of transistors packed into a dense integrated circuit doubles every 2 years. The corollary is that computation speed also doubles at 2-year intervals. Figure 1 is a graphical interpretation of Moore's Law, showing an exponential increase in computational power, in terms of calculations per second that can be purchased with $1000 (constant US, 2015). According to that graph, computing power has increased by a factor of 1018 from the mechanical analytical engine of the early 1900s to today's core I7 Quad chip found in personal laptop computers. The growth of computer power, based on calculations per second purchased by $1000 USD (constant 2015) during the past century. Also shown are significant developments in technology associated with increases in computer power.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure which appears, for instance, in the context of natural language processing, face recognition, fraud detection, and game intelligence. Although there exist a large number of numerical simulations in which GD type optimization schemes are effectively used to train ANNs with ReLU activation, till this day in the scientific literature there is in general no mathematical convergence analysis which explains the success of GD type optimization schemes in the training of such ANNs. GD type optimization schemes can be regarded as temporal discretization methods for the gradient flow (GF) differential equations associated to the considered optimization problem and, in view of this, it seems to be a natural direction of research to first aim to develop a mathematical convergence theory for time-continuous GF differential equations and, thereafter, to aim to extend such a time-continuous convergence theory to implementable time-discrete GD type optimization methods. Although there is in general no theoretical analysis which explains the success of GD type optimization schemes in the training of ANNs in the literature, there are several auspicious analysis approaches as well as several promising partial error analyses regarding the training of ANNs via GD type optimization schemes and GFs, respectively, in the literature. For convex objective functions, the convergence of GF and GD processes to the global minimum in different settings has been proved, e.g., in [5, 23, 34, 35, 38]. For general non-convex objective functions, even under smoothness assumptions GF and GD processes can show wild oscillations and admit infinitely many limit points, cf., e.g., [1]. A standard condition which excludes this undesirable behavior is the Lojasiewicz inequality and we point to [1, 3, 4, 8, 16, 28, 29, 30, 31, 33, 36] for convergence results for GF and GD processes under Lojasiewicz type assumptions.

We introduce a novel geometry-informed irreversible perturbation that accelerates convergence of the Langevin algorithm for Bayesian computation. It is well documented that there exist perturbations to the Langevin dynamics that preserve its invariant measure while accelerating its convergence. Irreversible perturbations and reversible perturbations (such as Riemannian manifold Langevin dynamics (RMLD)) have separately been shown to improve the performance of Langevin samplers. We consider these two perturbations simultaneously by presenting a novel form of irreversible perturbation for RMLD that is informed by the underlying geometry. Through numerical examples, we show that this new irreversible perturbation can improve performance of the estimator over reversible perturbations that do not take the geometry into account. Moreover we demonstrate that irreversible perturbations generally can be implemented in conjunction with the stochastic gradient version of the Langevin algorithm. Lastly, while continuous-time irreversible perturbations cannot impair the performance of a Langevin estimator, the situation can sometimes be more complicated when discretization is considered. To this end, we describe a discrete-time example in which irreversibility increases both the bias and variance of the resulting estimator.

In this paper we combine the k-means and/or k-means type algorithms with a hill climbing algorithm in stages to solve the joint stratification and sample allocation problem. This is a combinatorial optimisation problem in which we search for the optimal stratification from the set of all possible stratifications of basic strata. Each stratification being a solution the quality of which is measured by its cost. This problem is intractable for larger sets. Furthermore evaluating the cost of each solution is expensive. A number of heuristic algorithms have already been developed to solve this problem with the aim of finding acceptable solutions in reasonable computation times. However, the heuristics for these algorithms need to be trained in order to optimise performance in each instance. We compare the above multi-stage combination of algorithms with three recent algorithms and report the solution costs, evaluation times and training times. The multi-stage combinations generally compare well with the recent algorithms both in the case of atomic and continuous strata and provide the survey designer with a greater choice of algorithms to choose from.

Nonlinear stochastic modeling is useful for describing complex engineering systems. Meanwhile, neuromorphic (brain-inspired) computing paradigms are developing to tackle tasks that are challenging and resource intensive on digital computers. An emerging scheme is reservoir computing which exploits nonlinear dynamical systems for temporal information processing. This paper introduces reservoir computers with output feedback as stationary and ergodic infinite-order nonlinear autoregressive models. We highlight the versatility of this approach by employing classical and quantum reservoir computers to model synthetic and real data sets, further exploring their potential for control applications.

Musical instruments recognition is a widely used application for music information retrieval. As most of previous musical instruments recognition dataset focus on western musical instruments, it is difficult for researcher to study and evaluate the area of traditional Chinese musical instrument recognition. This paper propose a traditional Chinese music dataset for training model and performance evaluation, named ChMusic. This dataset is free and publicly available, 11 traditional Chinese musical instruments and 55 traditional Chinese music excerpts are recorded in this dataset. Then an evaluation standard is proposed based on ChMusic dataset. With this standard, researchers can compare their results following the same rule, and results from different researchers will become comparable.

The prediction of express delivery sequence, i.e., modeling and estimating the volumes of daily incoming and outgoing parcels for delivery, is critical for online business, logistics, and positive customer experience, and specifically for resource allocation optimization and promotional activity arrangement. A precise estimate of consumer delivery requests has to involve sequential factors such as shopping behaviors, weather conditions, events, business campaigns, and their couplings. Besides, conventional sequence prediction assumes a stable sequence evolution, failing to address complex nonlinear sequences and various feature effects in the above multi-source data. Although deep networks and attention mechanisms demonstrate the potential of complex sequence modeling, extant networks ignore the heterogeneous and coupling situation between features and sequences, resulting in weak prediction accuracy. To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features. DeepExpress leverages an express delivery seq2seq learning, a carefully-designed heterogeneous feature representation, and a novel joint training attention mechanism to adaptively map heterogeneous data, and capture sequence-feature coupling for precise estimation. Experimental results on real-world data demonstrate that the proposed method outperforms both shallow and deep baseline models.