Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO). In this setting, variational posteriors are often only partially conditioned. While the true posteriors depend, e.g., on the entire sequence of observations, approximate posteriors are only informed by past observations. This mimics the Bayesian filter -- a mixture of smoothing posteriors. Yet, we show that the ELBO objective forces partially-conditioned amortised posteriors to approximate products of smoothing posteriors instead. Consequently, the learned generative model is compromised. We demonstrate these theoretical findings in three scenarios: traffic flow, handwritten digits, and aerial vehicle dynamics. Using fully-conditioned approximate posteriors, performance improves in terms of generative modelling and multi-step prediction.

One of the biggest lessons Australia and New Zealand business leaders can take from the past 12 months is that a climate of uncertainty is now the new normal. The shift in customer behaviour brought about by the COVID-19 pandemic, coupled with rapid information technology changes, has already presented significant challenges. As a result, many organisations have had to bring forward their digital transformation plans and complete projects in weeks or months rather than years. During 2021, CIOs will have to work throughout their organisations and apply digital technologies and data to unlock new business opportunities. They must also work to promote a growth mindset that will help to unlock fresh innovation and agility. Adopting such a growth mindset will require CIOs and IT teams to embrace six key trends during the coming 12 months.

The edge of a network, as you may know, is the furthest extent of its reach. A cloud platform is a kind of network overlay that makes multiple network locations part of a single network domain. It should therefore stand to reason that an edge cloud is a single addressable, logical network at the furthest extent of a physical network. And an edge cloud on a global scale should be a way to make multiple, remote data centers accessible as a single pool of resources -- of processors, storage, and bandwidth. The combination of 5G and edge computing will unleash new capabilities from real-time analytics to automation to self-driving cars and trucks.

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its natural behavior of sequential optimization of the error function. This has led to the development of parallel SGD algorithms, such as asynchronous SGD (ASGD) and synchronous SGD (SSGD) to train deep neural networks. However, it introduces a high variance due to the delay in parameter (weight) update. We address this delay in our proposed algorithm and try to minimize its impact. We employed guided SGD (gSGD) that encourages consistent examples to steer the convergence by compensating the unpredictable deviation caused by the delay. Its convergence rate is also similar to A/SSGD, however, some additional (parallel) processing is required to compensate for the delay. The experimental results demonstrate that our proposed approach has been able to mitigate the impact of delay for the quality of classification accuracy. The guided approach with SSGD clearly outperforms sequential SGD and even achieves the accuracy close to sequential SGD for some benchmark datasets.

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models that rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse states of a dynamic model, which are used for invariant feature extraction. However, this inference and the corresponding backwards network parameter updating are major computational bottlenecks. They severely limit the network depths that can be reasonably implemented and easily trained. We therefore propose a optimization strategy, with better empirical and theoretical convergence, based on accelerated proximal gradients. We demonstrate that the ability to construct deeper DPCNs leads to receptive fields that capture well the entire notions of objects on which the networks are trained. This improves the feature representations. It yields completely unsupervised classifiers that surpass convolutional and convolutional-recurrent autoencoders and are on par with convolutional networks trained in a supervised manner. This is despite the DPCNs having orders of magnitude fewer parameters.

In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model reach a better calibration that is competitive to strong baselines, with little or no loss in accuracy. We discuss three variants of energy functions (namely scalar, hidden, and sharp-hidden) that can be defined on top of a text encoder, and compare them in experiments. Due to the discreteness of text data, we adopt noise contrastive estimation (NCE) to train the energy-based model. To make NCE training more effective, we train an auto-regressive noise model with the masked language model (MLM) objective.

Finding an expert plays a crucial role in driving successful collaborations and speeding up high-quality research development and innovations. However, the rapid growth of scientific publications and digital expertise data makes identifying the right experts a challenging problem. Existing approaches for finding experts given a topic can be categorised into information retrieval techniques based on vector space models, document language models, and graph-based models. In this paper, we propose $\textit{ExpFinder}$, a new ensemble model for expert finding, that integrates a novel $N$-gram vector space model, denoted as $n$VSM, and a graph-based model, denoted as $\textit{$\mu$CO-HITS}$, that is a proposed variation of the CO-HITS algorithm. The key of $n$VSM is to exploit recent inverse document frequency weighting method for $N$-gram words and $\textit{ExpFinder}$ incorporates $n$VSM into $\textit{$\mu$CO-HITS}$ to achieve expert finding. We comprehensively evaluate $\textit{ExpFinder}$ on four different datasets from the academic domains in comparison with six different expert finding models. The evaluation results show that $\textit{ExpFinder}$ is a highly effective model for expert finding, substantially outperforming all the compared models in 19% to 160.2%.

Understanding the actions of both humans and artificial intelligence (AI) agents is important before modern AI systems can be fully integrated into our daily life. In this paper, we show that, despite their current huge success, deep learning based AI systems can be easily fooled by subtle adversarial noise to misinterpret the intention of an action in interaction scenarios. Based on a case study of skeleton-based human interactions, we propose a novel adversarial attack on interactions, and demonstrate how DNN-based interaction models can be tricked to predict the participants' reactions in unexpected ways. From a broader perspective, the scope of our proposed attack method is not confined to problems related to skeleton data but can also be extended to any type of problems involving sequential regressions. Our study highlights potential risks in the interaction loop with AI and humans, which need to be carefully addressed when deploying AI systems in safety-critical applications.

We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final weights and how much it informs the function computed by the weights. Though related, we show that these quantities have a qualitatively different behavior. We give efficient approximations of these quantities using a linearized network and demonstrate empirically that the approximation is accurate for real-world architectures, such as pre-trained ResNets. We apply these measures to several problems, such as dataset summarization, analysis of under-sampled classes, comparison of informativeness of different data sources, and detection of adversarial and corrupted examples. Our work generalizes existing frameworks but enjoys better computational properties for heavily overparametrized models, which makes it possible to apply it to real-world networks. Training a deep neural network (DNN) entails extracting information from samples in a dataset and storing it in the weights of the network, so that it may be used in future inference or prediction. But how much information does a particular sample contribute to the trained model? The answer can be used to provide strong generalization bounds (if no information is used, the network is not memorizing the sample), privacy bounds (how much information the network can leak about a particular sample), and enable better interpretation of the training process and its outcome. To determine the information content of samples, we need to define and compute information. In the classical sense, information is a property of random variables, which may be degenerate for the deterministic process of computing the output of a trained DNN in response to a given input (inference). So, even posing the problem presents some technical challenges.

However, this progress is largely driven by increased computational power, namely GPU's, and bigger data sets but not due to radically new algorithms or knowledge representations. Artificial Neural Networks and Stochastic Gradient Descent, popularized in the 80's [3], remain the fundamental building blocks for most modern AI systems. While very successful for many applications, especially in vision, the purely deep-learning based approach has significant weaknesses. For instance, CNN's struggle with same-different relations [4], fail when long-chained reasoning is needed [5], are non-decomposable, cannot easily incorporate symbolic knowledge, and are hampered by a lack of model interpretability. Many current methods essentially compute higher order statistics over basic elements such as pixels, phonemes, letters or words to process inputs but do not explicitly model the building blocks and their relations in a (de)composable and interpretable way.