Learning word representations has garnered greater attention in the recent past due to its diverse text applications. W ord embed-dings encapsulate the syntactic and semantic regularities of sentences. Modelling word embedding as multi-sense gaussian mixture distributions, will additionally capture uncertainty and polysemy of words. W e propose to learn the Gaussian mixture representation of words using a Kullback-Leibler (KL) divergence based objective function. The KL divergence based energy function provides a better distance metric which can effectively capture entailment and distribution similarity among the words. Due to the intractability of KL divergence for Gaussian mixture, we go for a KL approximation between Gaussian mixtures. W e perform qualitative and quantitative experiments on benchmark word similarity and entailment datasets which demonstrate the effectiveness of the proposed approach.

The past decade has seen a remarkable series of advances in machine learning, and in particular deep learning approaches based on artificial neural networks, to improve our abilities to build more accurate systems across a broad range of areas, including computer vision, speech recognition, language translation, and natural language understanding tasks. This paper is a companion paper to a keynote talk at the 2020 International Solid-State Circuits Conference (ISSCC) discussing some of the advances in machine learning, and their implications on the kinds of computational devices we need to build, especially in the post-Moore's Law-era. It also discusses some of the ways that machine learning may also be able to help with some aspects of the circuit design process. Finally, it provides a sketch of at least one interesting direction towards much larger-scale multi-task models that are sparsely activated and employ much more dynamic, example- and task-based routing than the machine learning models of today.

One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art has focused on enforcing priors in the form of invariances to parametric nuisance transformations that are expected to be present in data. Learning non-parametric invariances directly from data remains an important open problem. In this paper, we introduce a new architectural layer for convolutional networks which is capable of learning general invariances from data itself. This layer can learn invariance to non-parametric transformations and interestingly, motivates and incorporates permanent random connectomes, thereby being called Permanent Random Connectome Non-Parametric Transformation Networks (PRC-NPTN). PRC-NPTN networks are initialized with random connections (not just weights) which are a small subset of the connections in a fully connected convolution layer. Importantly, these connections in PRC-NPTNs once initialized remain permanent throughout training and testing. Permanent random connectomes make these architectures loosely more biologically plausible than many other mainstream network architectures which require highly ordered structures. We motivate randomly initialized connections as a simple method to learn invariance from data itself while invoking invariance towards multiple nuisance transformations simultaneously. We find that these randomly initialized permanent connections have positive effects on generalization, outperform much larger ConvNet baselines and the recently proposed Non-Parametric Transformation Network (NPTN) on benchmarks that enforce learning invariances from the data itself.

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNNs. As an example, we construct a simple architecture that exceeds the expressiveness of the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theory on both synthetic and real-world benchmarks, and demonstrate our example's theoretical power translates to strong results on node classification, graph classification, and graph regression tasks.

Time delay estimation (TDE) is a critical and challenging step in all ultrasound elastography methods. A growing number of TDE techniques require an approximate but robust and fast method to initialize solving for TDE. Herein, we present a fast method for calculating an approximate TDE between two radio frequency (RF) frames of ultrasound. Although this approximate TDE can be useful for several algorithms, we focus on GLobal Ultrasound Elastography (GLUE), which currently relies on Dynamic Programming (DP) to provide this approximate TDE. We exploit Principal Component Analysis (PCA) to find the general modes of deformation in quasi-static elastography, and therefore call our method PCA-GLUE. PCA-GLUE is a data-driven approach that learns a set of TDE principal components from a training database in real experiments. In the test phase, TDE is approximated as a weighted sum of these principal components. Our algorithm robustly estimates the weights from sparse feature matches, then passes the resulting displacement field to GLUE as initial estimates to perform a more accurate displacement estimation. PCA-GLUE is more than ten times faster than DP in estimation of the initial displacement field and yields similar results.

To overcome the high dimensionality of data, learning latent feature representations for clustering has been widely studied recently. However, it is still challenging to learn "cluster-friendly" latent representations due to the unsupervised fashion of clustering. In this paper, we propose Disentangling Latent Space Clustering (DLS-Clustering), a new clustering mechanism that directly learning cluster assignment during the disentanglement of latent spacing without constructing the "cluster-friendly" latent representation and additional clustering methods. We achieve the bidirectional mapping by enforcing an inference network (i.e. encoder) and the generator of GAN to form a deterministic encoder-decoder pair with a maximum mean discrepancy (MMD)-based regularization. We utilize a weight-sharing procedure to disentangle latent space into the one-hot discrete latent variables and the continuous latent variables. The disentangling process is actually performing the clustering operation. Eventually the one-hot discrete latent variables can be directly expressed as clusters, and the continuous latent variables represent remaining unspecified factors. Experiments on six benchmark datasets of different types demonstrate that our method outperforms existing state-of-the-art methods. We further show that the latent representations from DLS-Clustering also maintain the ability to generate diverse and high-quality images, which can support more promising application scenarios.

Machine Learning as a Service (MLaaS) is enabling a wide range of smart applications on end devices. However, such convenience comes with a cost of privacy because users have to upload their private data to the cloud. This research aims to provide effective and efficient MLaaS such that the cloud server learns nothing about user data and the users cannot infer the proprietary model parameters owned by the server. This work makes the following contributions. First, it unveils the fundamental performance bottleneck of existing schemes due to the heavy permutations in computing linear transformation and the use of communication intensive Garbled Circuits for nonlinear transformation. Second, it introduces an ultra-fast secure MLaaS framework, CHEETAH, which features a carefully crafted secret sharing scheme that runs significantly faster than existing schemes without accuracy loss. Third, CHEETAH is evaluated on the benchmark of well-known, practical deep networks such as AlexNet and VGG-16 on the MNIST and ImageNet datasets. The results demonstrate more than 100x speedup over the fastest GAZELLE (Usenix Security'18), 2000x speedup over MiniONN (ACM CCS'17) and five orders of magnitude speedup over CryptoNets (ICML'16). This significant speedup enables a wide range of practical applications based on privacy-preserved deep neural networks.

Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and face recognition, classification of large volumes of web data, and finance. The bottleneck is that neural network training involves iterative gradient descent and is extremely computationally intensive. In this paper we present a technique for distributed training of Ultra Large Scale Neural Networks (ULSNN) on Bunyip, a Linux-based cluster of 196 Pentium III processors. To illustrate ULSNN training we describe an experiment in which a neural network with 1.73 million adjustable parameters was trained to recognize machine-printed Japanese characters from a database containing 9 million training patterns. The training runs with a average performance of 163.3 GFlops/s (single precision). With a machine cost of \$150,913, this yields a price/performance ratio of 92.4c/MFlops/s (single precision). For comparison purposes, training using double precision and the ATLAS DGEMM produces a sustained performance of 70 MFlops/s or \$2.16 / MFlop/s (double precision).

We consider the stochastic nested composition optimization problem where the objective is a composition of two expected-value functions. We proposed the stochastic ADMM to solve this complicated objective. In order to find an $\epsilon$ stationary point where the expected norm of the subgradient of corresponding augmented Lagrangian is smaller than $\epsilon$, the total sample complexity of our method is $\mathcal{O}(\epsilon^{-3})$ for the online case and $\mathcal{O} \Bigl((2N_1 + N_2) + (2N_1 + N_2)^{1/2}\epsilon^{-2}\Bigr)$ for the finite sum case. The computational complexity is consistent with proximal version proposed in \cite{zhang2019multi}, but our algorithm can solve more general problem when the proximal mapping of the penalty is not easy to compute.

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL). NS3L is motivated by the success of negative sampling/contrastive estimation. We demonstrate that adding the NS3L loss to state-of-the-art SSL algorithms, such as the Virtual Adversarial Training (VAT), significantly improves upon vanilla VAT and its variant, VAT with Entropy Minimization. By adding the NS3L loss to MixMatch, the current state-of-the-art approach on semi-supervised tasks, we observe significant improvements over vanilla MixMatch. We conduct extensive experiments on the CIFAR10, CIFAR100, SVHN and STL10 benchmark datasets.