We consider wireless transmission of images in the presence of channel output feedback. From a Shannon theoretic perspective feedback does not improve the asymptotic end-to-end performance, and separate source coding followed by capacity achieving channel coding achieves the optimal performance. Although it is well known that separation is not optimal in the practical finite blocklength regime, there are no known practical joint source-channel coding (JSCC) schemes that can exploit the feedback signal and surpass the performance of separate schemes. Inspired by the recent success of deep learning methods for JSCC, we investigate how noiseless or noisy channel output feedback can be incorporated into the transmission system to improve the reconstruction quality at the receiver. We introduce an autoencoder-based deep JSCC scheme that exploits the channel output feedback, and provides considerable improvements in terms of the end-to-end reconstruction quality for fixed length transmission, or in terms of the average delay for variable length transmission. To the best of our knowledge, this is the first practical JSCC scheme that can fully exploit channel output feedback, demonstrating yet another setting in which modern machine learning techniques can enable the design of new and efficient communication methods that surpass the performance of traditional structured coding-based designs.

Sparse neural networks have been shown to be more parameter and compute efficient compared to dense networks and in some cases are used to decrease wall clock inference times. There is a large body of work on training dense networks to yield sparse networks for inference (Molchanov et al., 2017; Zhu & Gupta, 2018; Narang et al., 2017; Li et al., 2016; Guo et al., 2016). This limits the size of the largest trainable sparse model to that of the largest trainable dense model. In this paper we introduce a method to train sparse neural networks with a fixed parameter count and a fixed computational cost throughout training, without sacrificing accuracy relative to existing dense-to-sparse training methods. We show that this approach requires fewer floating-point operations (FLOPs) to achieve a given level of accuracy compared to prior techniques. Importantly,by adjusting the topology it can start from any initialization - not just "lucky" ones. We demonstrate state-of-the-art sparse training results with ResNet-50, MobileNet v1 and MobileNet v2 on the ImageNet-2012 dataset, WideResNets on the CIFAR-10 dataset and RNNs on the WikiText-103 dataset. Finally, we provide some insights into why allowing the topology to change during the optimization can overcome local minima encountered when the topology remains static. 1 Introduction The parameter and floating point operation (FLOP) efficiency of sparse neural networks is now well demonstrated on a variety of problems (Han et al., 2015; Srinivas et al., 2017). Multiple works have shown inference time speedups are possible using sparsity for both Recurrent Neural Networks (RNNs) (Kalchbrenner et al., 2018) and Convolutional Neural Networks (ConvNets) (Park et al., 2016; Elsen et al., 2019). Currently, the most accurate sparse models are obtained with techniques that require, at a minimum, the cost of training a dense model in terms of memory and FLOPs (Zhu & Gupta, 2018; Guo et al., 2016), and sometimes significantly more (Molchanov et al., 2017). This paradigm has two main limitations: 1. The maximum size of sparse models is limited to the largest dense model that can be trained. Even if sparse models are more parameter efficient, we can't use pruning to train models that are larger and more accurate than the largest possible dense models. Large amounts of computation must be performed for parameters that are zero valued or that will be zero during inference. Gale et al. (2019) found that three different dense-to-sparse training algorithms all achieve about the same sparsity / accuracy tradeoff.

Currently, the diagnosis of Autism Spectrum Disorder (ASD) is dependent upon a subjective, time-consuming evaluation of behavioral tests by an expert clinician. Non-invasive functional MRI (fMRI) characterizes brain connectivity and may be used to inform diagnoses and democratize medicine. However, successful construction of deep learning models from fMRI requires addressing key choices about the model's architecture, including the number of layers and number of neurons per layer. Meanwhile, deriving functional connectivity (FC) features from fMRI requires choosing an atlas with an appropriate level of granularity. Once a model has been built, it is vital to determine which features are predictive of ASD and if similar features are learned across atlas granularity levels. To identify aptly suited architectural configurations, probability distributions of the configurations of high versus low performing models are compared. To determine the effect of atlas granularity, connectivity features are derived from atlases with 3 levels of granularity and important features are ranked with permutation feature importance. Results show the highest performing models use between 2-4 hidden layers and 16-64 neurons per layer, granularity dependent. Connectivity features identified as important across all 3 atlas granularity levels include FC to the supplementary motor gyrus and language association cortex, regions associated with deficits in social and sensory processing in ASD. Importantly, the cerebellum, often not included in functional analyses, is also identified as a region whose abnormal connectivity is highly predictive of ASD. Results of this study identify important regions to include in future studies of ASD, help assist in the selection of network architectures, and help identify appropriate levels of granularity to facilitate the development of accurate diagnostic models of ASD.

The information bottleneck (IB) problem tackles the issue of obtaining relevant compressed representations T of some random variable X for the task of predicting Y. It is defined as a constrained optimization problem which maximizes the information the representation has about the task, I(T;Y), while ensuring that a minimum level of compression r is achieved; i.e., I(X;T) <= r. For practical reasons the problem is usually solved by maximizing the IB Lagrangian for many values of the Lagrange multiplier, therefore drawing the IB curve (i.e., the curve of maximal I(T;Y) for a given I(X;T)) and selecting the representation of desired predictability and compression. It is known when Y is a deterministic function of X, the IB curve cannot be explored, and other Lagrangians have been proposed to tackle this problem; e.g., the squared IB Lagrangian. In this paper, we (i) present a general family of Lagrangians which allow for the exploration of the IB curve in all scenarios; and (ii) prove that if these Lagrangians are used, there is a (and we know the) one-to-one mapping between the Lagrange multiplier and the desired compression rate r for known IB curve shapes, hence, freeing us from the burden of solving the optimization problem for many values of the Lagrange multiplier. That is, we can solve the original constrained problem with a single optimization.

In this paper we present a model for unsupervised topic discovery in texts corpora. The proposed model uses documents, words, and topics lookup table embedding as neural network model parameters to build probabilities of words given topics, and probabilities of topics given documents. These probabilities are used to recover by marginalization probabilities of words given documents. For very large corpora where the number of documents can be in the order of billions, using a neural auto-encoder based document embedding is more scalable then using a lookup table embedding as classically done. We thus extended the lookup based document embedding model to continuous auto-encoder based model. Our models are trained using probabilistic latent semantic analysis (PLSA) assumptions. We evaluated our models on six datasets with a rich variety of contents. Conducted experiments demonstrate that the proposed neural topic models are very effective in capturing relevant topics. Furthermore, considering perplexity metric, conducted evaluation benchmarks show that our topic models outperform latent Dirichlet allocation (LDA) model which is classically used to address topic discovery tasks.

Iterative learning to infer approaches have become popular solvers for inverse problems. However, their memory requirements during training grow linearly with model depth, limiting in practice model expressiveness. In this work, we propose an iterative inverse model with constant memory that relies on invertible networks to avoid storing intermediate activations. As a result, the proposed approach allows us to train models with 400 layers on 3D volumes in an MRI image reconstruction task. In experiments on a public data set, we demonstrate that these deeper, and thus more expressive, networks perform state-of-the-art image reconstruction.

Existing methods produce very inefficient architectures and do not scale. In this paper, we introduce a new method for generating data from a random forest and learning a neural network that imitates it. Without any additional training data, this transformation creates very efficient neural networks that learn the decision boundaries of a random forest. The generated model is fully differentiable and can be combined with the feature extraction in a single pipeline enabling further end-to-end processing. Experiments on several real-world benchmark datasets demonstrate outstanding performance in terms of scalability, accuracy, and learning with very few training examples. Compared to state-of-the-art mappings, we significantly reduce the network size while achieving the same or even improved accuracy due to better generalization.

This study investigates a new constrained-optimization formulation for deep ordinal classification. We impose uni-modality of the label distribution implicitly via a set of inequality constraints over pairs of adjacent labels. To tackle the ensuing challenging optimization problem, we solve a sequence of unconstrained losses based on a powerful extension of the log-barrier method. This accommodates standard SGD for deep networks, and avoids computationally expensive Lagrangian dual steps and projections, while outperforming substantially penalty methods. Our non-parametric model is more flexible than the existing deep ordinal classification techniques: it does not restrict the learned representation to a specific parametric model, allowing the training to explore larger spaces of solutions and removing the need for ad hoc choices, while scaling up to large numbers of labels. It can be used in conjunction with any standard classification loss and any deep architecture. We also propose a new performance metric for ordinal classification, as a proxy to measure a distribution uni-modality, referred to as the Sides Order Index (SOI). We report comprehensive evaluations and comparisons to state-of-the-art methods on benchmark public datasets for several ordinal classification tasks, showing the merits of our approach in terms of label consistency and scalability. A public reproducible PyTorch implementation is provided (https://github.com/sbelharbi/Deep-Ordinal-Classification-with-Inequality-Constraints).

With the ever-increasing reliance on data for data-driven applications in power grids, such as event cause analysis, the authenticity of data streams has become crucially important. The data can be prone to adversarial stealthy attacks aiming to manipulate the data such that residual-based bad data detectors cannot detect them, and the perception of system operators or event classifiers changes about the actual event. This paper investigates the impact of adversarial attacks on convolutional neural network-based event cause analysis frameworks. We have successfully verified the ability of adversaries to maliciously misclassify events through stealthy data manipulations. The vulnerability assessment is studied with respect to the number of compromised measurements. Furthermore, a defense mechanism to robustify the performance of the event cause analysis is proposed. The effectiveness of adversarial attacks on changing the output of the framework is studied using the data generated by real-time digital simulator (RTDS) under different scenarios such as type of attacks and level of access to data.

W e explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be gleaned by probing deep into its weights. W e propose a method for "scrubbing" the weights clean of information about a particular set of training data. The method does not require retraining from scratch, nor access to the data originally used for training. Instead, the weights are modified so that any probing function of the weights, computed with no knowledge of the random seed used for training, is indistinguishable from the same function applied to the weights of a network trained without the data to be forgotten. This condition is a generalized and weaker form of Differential Privacy. Exploiting ideas related to the stability of stochastic gradient descent, we introduce an upper-bound on the amount of information remaining in the weights, which can be estimated efficiently even for deep neural networks.