Artificial neural networks thrive in solving the classification problem for a particular rigid task, where the network resembles a static entity of knowledge, acquired through generalized learning behaviour from a distinct training phase. However, endeavours to extend this knowledge without targeting the original task usually result in a catastrophic forgetting of this task. Continual learning shifts this paradigm towards a network that can continually accumulate knowledge over different tasks without the need for retraining from scratch, with methods in particular aiming to alleviate forgetting. We focus on task-incremental classification, where tasks arrive in a batch-like fashion, and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 10 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize which method performs best, both on balanced Tiny Imagenet and a large-scale unbalanced iNaturalist datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.

In recent years, mobile devices have gained increasingly development with stronger computation capability and larger storage. Some of the computation-intensive machine learning and deep learning tasks can now be run on mobile devices. To take advantage of the resources available on mobile devices and preserve users' privacy, the idea of mobile distributed machine learning is proposed. It uses local hardware resources and local data to solve machine learning sub-problems on mobile devices, and only uploads computation results instead of original data to contribute to the optimization of the global model. This architecture can not only relieve computation and storage burden on servers, but also protect the users' sensitive information. Another benefit is the bandwidth reduction, as various kinds of local data can now participate in the training process without being uploaded to the server. In this paper, we provide a comprehensive survey on recent studies of mobile distributed machine learning. We survey a number of widely-used mobile distributed machine learning methods. We also present an in-depth discussion on the challenges and future directions in this area. We believe that this survey can demonstrate a clear overview of mobile distributed machine learning and provide guidelines on applying mobile distributed machine learning to real applications.

Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks. We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Computers (DNC) to machine translation. We further propose and evaluate two models which extend the attentional encoder-decoder with capabilities inspired by memory augmented neural networks. We evaluate our proposed models on IWSLT Vietnamese to English and ACL Romanian to English datasets. Our proposed models and the memory augmented neural networks perform similarly to the attentional encoder-decoder on the Vietnamese to English translation task while have a 0.3-1.9 lower BLEU score for the Romanian to English task. Interestingly, our analysis shows that despite being equipped with additional flexibility and being randomly initialized memory augmented neural networks learn an algorithm for machine translation almost identical to the attentional encoder-decoder.

We study the effect of the introduction of university tuition fees on the enrollment behavior of students in Germany. For this, an appropriate Lasso-technique is crucial in order to identify the magnitude and significance of the effect due to potentially many relevant controlling factors and only a short time frame where fees existed. We show that a post-double selection strategy combined with stability selection determines a significant negative impact of fees on student enrollment and identifies relevant variables. This is in contrast to previous empirical studies and a plain linear panel regression which cannot detect any effect of tuition fees in this case. In our study, we explicitly deal with data challenges in the response variable in a transparent way and provide respective robust results. Moreover, we control for spatial cross-effects capturing the heterogeneity in the introduction scheme of fees across federal states ("Bundesl\"ander"), which can set their own educational policy. We also confirm the validity of our Lasso approach in a comprehensive simulation study.

With the advent of deep learning, the performance of text classification models have been improved significantly. Nevertheless, the successful training of a good classification model requires a sufficient amount of labeled data, while it is always expensive and time consuming to annotate data. With the rapid growth of digital data, similar classification tasks can typically occur in multiple domains, while the availability of labeled data can largely vary across domains. Some domains may have abundant labeled data, while in some other domains there may only exist a limited amount (or none) of labeled data. Meanwhile text classification tasks are highly domain-dependent -- a text classifier trained in one domain may not perform well in another domain. In order to address these issues, in this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.

A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objective functions are often not available, our understanding of the optimization problems is limited. Building on recent work on analyzing neural network training, we contribute novel visualizations of high-dimensional control optimization landscapes; this yields insights into why control optimization is hard and why common practices like early termination and spline-based action parameterizations make optimization easier. For example, our experiments show how trajectory optimization can become increasingly ill-conditioned with longer trajectories, but parameterizing control as partial target states - e.g., target angles converted to torques using a PD-controller - can act as an efficient preconditioner. Both our visualizations and quantitative empirical data also indicate that neural network policy optimization scales better than trajectory optimization for long planning horizons. Our work advances the understanding of movement optimization and our visualizations should also provide value in educational use.

A common approach for defining a reward function for Multi-objective Reinforcement Learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a new solution is required for any change in these settings. This paper investigates the relationship between the reward function and the optimal value function for MORL; specifically addressing the question of how to approximate the optimal value function well beyond the set of weights for which the optimization problem was actually solved, thereby avoiding the need to recompute for any particular choice. We prove that the value function transforms smoothly given a transformation of weights of the reward function (and thus a smooth interpolation in the policy space). A Gaussian process is used to obtain a smooth interpolation over the reward function weights of the optimal value function for three well-known examples: GridWorld, Objectworld and Pendulum. The results show that the interpolation can provide very robust values for sample states and action space in discrete and continuous domain problems. Significant advantages arise from utilizing this interpolation technique in the domain of autonomous vehicles: easy, instant adaptation of user preferences while driving and true randomization of obstacle vehicle behavior preferences during training.

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often needed to be solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the prior states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of widely adopted OPF linear DC approximation by at least two orders of magnitude.

Memory in an agent system is a process of reasoning: it is the l earning process of strengthening a concept. The interaction between an agent and the environment can pla y an important role in constructing its memory and may affect its future behaviour. In fact, through memory an agent is potentially able to recall and to learn from experiences so that its beliefs and i ts future course of action are grounded in these experiences. In computational logic, [2] introduces DLEK (Dynamic Logic of Explicit beliefs and Knowledge) as a logical formalization of the short-term and long-term memory. The underlying idea is to represent reasoning about the formation of beliefs throu gh perception and inference in non-omniscient resource-bounded agents. DLEK has however no notion of time, while agents' actual perceptions are inherently timed and so are many of the inferences drawn from such perceptions. In this paper we present an extension of LEK/DLEK to T-LEK/T-DLEK ("Timed LE K" and "Timed DLEK") obtained by introducing a special function which associates to each b elief the arrival time and controls timed inferences. Through this function it is easier to keep the ev olution of the surrounding world under control and the representation is more complete. This abstr act is an evolution version of [3], where we have introduced explicit time instants and time intervals i n formulas, and it is extracted from [4].

Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry. By contrast, human learning is significantly faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a Planner-Actor-Critic architecture for huMAN-centered planning and learning (PACMAN), where an agent uses its prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions, and also integrates the Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. This work is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.