We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Such an alignment assumption is invalidated in real world scenarios where some source classes are often under-represented or simply absent in the target domain. We revise the current approaches to class imbalance and propose a new one that uses latent codes in the adversarial domain adaptation framework. We show how the latent codes can be used to disentangle the silent structure of the target domain and to identify under-represented classes. We show how to learn the latent code reconstruction jointly with the domain invariant representation and use them to accurately estimate the target labels.

A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work. SSL contains four key ingredients: 1) successive near-to-far neighborhood expansion; 2) unsupervised dimension reduction via subspace approximation; 3) supervised dimension reduction via label-assisted regression (LAG); and 4) feature concatenation and decision making. An image-based object classification method, called PixelHop, is proposed to illustrate the SSL design. It is shown by experimental results that the PixelHop method outperforms the classic CNN model of similar model complexity in three benchmarking datasets (MNIST, Fashion MNIST and CIFAR-10). Although SSL and deep learning (DL) have some high-level concept in common, they are fundamentally different in model formulation, the training process and training complexity. Extensive discussion on the comparison of SSL and DL is made to provide further insights into the potential of SSL.

Automatic question generation is an important problem in natural language processing. In this paper we propose a novel adaptive copying recurrent neural network model to tackle the problem of question generation from sentences and paragraphs. The proposed model adds a copying mechanism component onto a bidirectional LSTM architecture to generate more suitable questions adaptively from the input data. Our experimental results show the proposed model can outperform the state-of-the-art question generation methods in terms of BLEU and ROUGE evaluation scores.

-- The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global source and target distributions, or pay attention to align subdomains based on multiple discriminators. However, in real applications, the marginal (global) and conditional (local) distributions between domains are often contributing differently to the adaptation. There is currently no method to dynamically and quantitatively evaluate the relative importance of these two distributions for adversarial learning. In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions. T o the best of our knowledge, DAAN is the first attempt to perform dynamic adversarial distribution adaptation for deep adversarial learning. DAAN is extremely easy to implement and train in real applications. We theoretically analyze the effectiveness of DAAN, and it can also be explained in an attention strategy. Extensive experiments demonstrate that DAAN achieves better classification accuracy compared to state-of-the-art deep and adversarial methods. Results also imply the necessity and effectiveness of the dynamic distribution adaptation in adversarial transfer learning.

Electricity consumption has increased exponentially during the past few decades. This increase is heavily burdening the electricity distributors. Therefore, predicting the future demand for electricity consumption will provide an upper hand to the electricity distributor. Predicting electricity consumption requires many parameters. The paper presents two approaches with one using a Recurrent Neural Network (RNN) and another one using a Long Short Term Memory (LSTM) network, which only considers the previous electricity consumption to predict the future electricity consumption. These models were tested on the publicly available London smart meter dataset. To assess the applicability of the RNN and the LSTM network to predict electricity consumption, they were tested to predict for an individual house and a block of houses for a given time period. The predictions were done for daily, trimester and 13 months, which covers short term, mid-term and long term prediction. Both the RNN and the LSTM network have achieved an average Root Mean Square error of 0.1.

The evolution of a deep neural network trained by the gradient descent can be described by its neural tangent kernel (NTK) as introduced in [20], where it was proven that in the infinite width limit the NTK converges to an explicit limiting kernel and it stays constant during training. The NTK was also implicit in some other recent papers [6,13,14]. In the overparametrization regime, a fully-trained deep neural network is indeed equivalent to the kernel regression predictor using the limiting NTK. And the gradient descent achieves zero training loss for a deep overparameterized neural network. However, it was observed in [5] that there is a performance gap between the kernel regression using the limiting NTK and the deep neural networks. This performance gap is likely to originate from the change of the NTK along training due to the finite width effect. The change of the NTK along the training is central to describe the generalization features of deep neural networks. In the current paper, we study the dynamic of the NTK for finite width deep fully-connected neural networks. We derive an infinite hierarchy of ordinary differential equations, the neural tangent hierarchy (NTH) which captures the gradient descent dynamic of the deep neural network. Moreover, under certain conditions on the neural network width and the data set dimension, we prove that the truncated hierarchy of NTH approximates the dynamic of the NTK up to arbitrary precision. This description makes it possible to directly study the change of the NTK for deep neural networks, and sheds light on the observation that deep neural networks outperform kernel regressions using the corresponding limiting NTK.

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation, two fields that fall into the framework of learning from Positive and Unlabeled data. In this paper, we stress the different drawbacks of the current family of softmax losses and sampling schemes when applied in a Positive and Unlabeled learning setup. We propose both a Relaxed Softmax loss (RS) and a new negative sampling scheme based on Boltzmann formulation. We show that the new training objective is better suited for the tasks of density estimation, item similarity and next-event prediction by driving uplifts in performance on textual and recommendation datasets against classical softmax.

Hardware architectures composed of resistive cross-point device arrays can provide significant power and speed benefits for deep neural network training workloads using stochastic gradient descent (SGD) and backpropagation (BP) algorithm. The training accuracy on this imminent analog hardware however strongly depends on the switching characteristics of the cross-point elements. One of the key requirements is that these resistive devices must change conductance in a symmetrical fashion when subjected to positive or negative pulse stimuli. Here, we present a new training algorithm, so-called the "Tiki-Taka" algorithm, that eliminates this stringent symmetry requirement. We show that device asymmetry introduces an unintentional implicit cost term into the SGD algorithm, whereas in the "Tiki-Taka" algorithm a coupled dynamical system simultaneously minimizes the original objective function of the neural network and the unintentional cost term due to device asymmetry in a self-consistent fashion. We tested the validity of this new algorithm on a range of network architectures such as fully connected, convolutional and LSTM networks. Simulation results on these various networks show that whatever accuracy is achieved using the conventional SGD algorithm with symmetric (ideal) device switching characteristics the same accuracy is also achieved using the "Tiki-Taka" algorithm with non-symmetric (non-ideal) device switching characteristics. Moreover, all the operations performed on the arrays are still parallel and therefore the implementation cost of this new algorithm on array architectures is minimal; and it maintains the aforementioned power and speed benefits. These algorithmic improvements are crucial to relax the material specification and to realize technologically viable resistive crossbar arrays that outperform digital accelerators for similar training tasks.

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small perturbations in the form of misspellings or paraphrases can drastically change the semantics of the text. We propose a reinforcement learning based approach towards generating adversarial examples in black-box settings. We demonstrate that our method is able to fool well-trained models for (a) IMDB sentiment classification task and (b) AG's news corpus news categorization task with significantly high success rates. We find that the adversarial examples generated are semantics-preserving perturbations to the original text.

This literature review focuses on three important aspects of an autonomous car system: tracking (assessing the identity of the actors such as cars, pedestrians or obstacles in a sequence of observations), prediction (predicting the future motion of surrounding vehicles in order to navigate through various traffic scenarios) and decision making (analyzing the available actions of the ego car and their consequences to the entire driving context). For tracking and prediction, approaches based on (deep) neural networks and other, especially stochastic techniques, are reported. For decision making, deep reinforcement learning algorithms are presented, together with methods used to explore different alternative actions, such as Monte Carlo Tree Search.