In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers not only to accurately classify the seen classes, but also to effectively deal with the unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, experiment setup and evaluation metrics. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also overview the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

Attributed to its high learning capacity with good prediction capability, the deep neural network has found its advantage in wide areas of science and engineering applications. Such an observation has sparked a surge of investigations into the architectural and learning aspects of the deep network for targeted applications. The main ground for realizing the high learning capacity and predictivity comes from several major advancements in the field which include the processing platform, the learning regimen, and the availability of big data size. In terms of the processing platform, the advancement in Graphics Processing Units (GPUs) has facilitated parallel processing of complex network learning within accessible time. Together with the relatively low cost of the hardware, the large number of public high level open source libraries has enabled a crowdsourcing mode of learning architectural exploration. Based on such a learning platform, several learning regimens such as the Convolutional Neural Network (CNN or LeNet-5) [1], the AlexNet [2], the GoogLeNet or Inception [3], the Visual Geometry Group Network (VGG Net) [4], the Residual Network (ResNet) [5] and the DenseNet [6] have stretched the network learning in terms of the network depth and prediction capability way beyond the known boundary established by the conventional statistical methods. 2 Without sufficiently convincing explanation in theory, the advancement of deep learning has been grounded upon'big' data, powerful machinery and crowd efforts to achieve at'breakthrough' results that were not possible before. Such a swarming phenomenon has pushed forward the demand of hardware as well as middle ware, but at the expense of masking the importance of fundamental results available in statistical decision theory. The research scene has arrived at such a state of deeming results unacceptable without working directly on or comparing them with'big' data which implicitly relies on powerful machinery.

Noname manuscript No. (will be inserted by the editor) Abstract Learning classifier systems are evolutionary machine learning algorithms, flexible enough to be applied toreinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifierswere proposed which are similar to learning classifier systems but have the advantage that in its structured population no balance between niching and fitness pressure is necessary. However, more tests and analysis are required to verify its benefits. Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM). This algorithm isapplied in challenging problems such as big, noisy as well as dynamically changing continuous inputaction mazes(growing and compressing mazes are included) withgood performance. Moreover, a genetic operator is proposed which utilizes the topological information ofthe SOM's population structure, improving the results. Thus, the first steps in structured evolutionary machinelearning are shown, nonetheless, the problems faced are more difficult than the state-of-art continuous input-action multi-step ones. 1 Introduction Learning Classifier Systems (LCS) are several algorithms inspired by evolution [29],[20]. Different from most reinforcement learning algorithms, however, LCS algorithms do not use state-action lookup tables to predict payoff. In this manner, the difficulties that arrive from complex problems, wherea large number of states and/or actions are required, can be avoided. Oneway of solving this problem is to separate a fitness defined on a niche from fitnesses defined on other niches (i.e., having a good fitness on other niches would not influence the present niche).

Generative Adversarial Nets (GANs) are emerging objects of study in machine learning, computer vision, natural language processing, and many other domains. In machine learning, study of such a framework has led to significant advances in adversarial defenses [28, 24] and machine security [4, 24]. In computer vision and natural language processing, GANs have resulted in improved performance over standard generative models for images and texts [13], such as variational autoencoder [16] and deep Boltzmann machine [22]. A main technique to achieve this goal is to play a minimax two-player game between generator and discriminator under the design that the generator tries to confuse the discriminator with its generated contents and the discriminator tries to distinguish real images/texts from what the generator creates. Despite a large amount of variants of GANs, many fundamental questions remain unresolved. One of the longstanding challenges is designing universal, easy-to-implement architectures that alleviate the instability issue of GANs training. Ideally, GANs are supposed to solve the minimax optimization problem [13], but in practice alternating gradient descent methods do not clearly privilege minimax over maximin or vice versa (page 35, [12]), which may lead to instability in training if there exists a large discrepancy between the minimax and maximin objective values. The focus of this work is on improving the stability of such minimax game in the training process of GANs. 1 Under review as a conference paper at ICLR 2019

We develop theory for using heuristics to solve computationally hard problems in differential privacy. Heuristic approaches have enjoyed tremendous success in machine learning, for which performance can be empirically evaluated. However, privacy guarantees cannot be evaluated empirically, and must be proven --- without making heuristic assumptions. We show that learning problems over broad classes of functions can be solved privately and efficiently, assuming the existence of a non-private oracle for solving the same problem. Our first algorithm yields a privacy guarantee that is contingent on the correctness of the oracle. We then give a reduction which applies to a class of heuristics which we call certifiable, which allows us to convert oracle-dependent privacy guarantees to worst-case privacy guarantee that hold even when the heuristic standing in for the oracle might fail in adversarial ways. Finally, we consider a broad class of functions that includes most classes of simple boolean functions studied in the PAC learning literature, including conjunctions, disjunctions, parities, and discrete halfspaces. We show that there is an efficient algorithm for privately constructing synthetic data for any such class, given a non-private learning oracle. This in particular gives the first oracle-efficient algorithm for privately generating synthetic data for contingency tables. The most intriguing question left open by our work is whether or not every problem that can be solved differentially privately can be privately solved with an oracle-efficient algorithm. While we do not resolve this, we give a barrier result that suggests that any generic oracle-efficient reduction must fall outside of a natural class of algorithms (which includes the algorithms given in this paper).

In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a priori low test accuracy. We are motivated by applications in interpretability and model deployment in severely memory constrained environments (like sensors). Our method uses linear probes to generate confidence scores through flattened intermediate representations. Our transfer method involves a theoretically justified weighting of samples during the training of the simple model using confidence scores of these intermediate layers. The value of our method is first demonstrated on CIFAR-10, where our weighting method significantly improves (3-4%) networks with only a fraction of the number of Resnet blocks of a complex Resnet model. We further demonstrate operationally significant results on a real manufacturing problem, where we dramatically increase the test accuracy of a CART model (the domain standard) by roughly 13%.

Person re-identification (ReID) is aimed at identifying the same person across videos captured from different cameras. In the view that networks extracting global features using ordinary network architectures are difficult to extract local features due to their weak attention mechanisms, researchers have proposed a lot of elaborately designed ReID networks, while greatly improving the accuracy, the model size and the feature extraction latency are also soaring. We argue that a relatively compact ordinary network extracting globally pooled features has the capability to extract discriminative local features and can achieve state-of-the-art precision if only the model's parameters are properly learnt. In order to reduce the difficulty in learning hard identity labels, we propose a novel knowledge distillation method: Factorized Distillation, which factorizes both feature maps and retrieval features of holistic ReID network to mimic representations of multiple partial ReID models, thus transferring the knowledge from partial ReID models to the holistic network. Experiments show that the performance of model trained with the proposed method can outperform state-of-the-art with relatively few network parameters.

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their disadvantages: reward functions require manual engineering, while demonstrations require a human expert to be able to actually perform the task in order to generate the demonstration. Instruction following from natural language instructions provides an appealing alternative: in the same way that we can specify goals to other humans simply by speaking or writing, we would like to be able to specify tasks for our machines. However, a single instruction may be insufficient to fully communicate our intent or, even if it is, may be insufficient for an autonomous agent to actually understand how to perform the desired task. In this work, we propose an interactive formulation of the task specification problem, where iterative language corrections are provided to an autonomous agent, guiding it in acquiring the desired skill. Our proposed language-guided policy learning algorithm can integrate an instruction and a sequence of corrections to acquire new skills very quickly. In our experiments, we show that this method can enable a policy to follow instructions and corrections for simulated navigation and manipulation tasks, substantially outperforming direct, non-interactive instruction following.

Max Tegmark's Life 3.0: Being Human in the Age of Artificial Intelligence stretches one's mind and imagination on how life could be, not just a few decades from now, but billions of years ahead. By Life 1.0, the scientist refers to our biological evolution based on DNA. Life 2.0 is about our current'cultural development' stage where we can remodel much of our'software,' e.g. The main focus of the book is of course "Life 3.0" where artificial general intelligence may someday, in addition to being able to learn, be able to redesign its own hardware and software. I strongly recommend the book if you have not read it already.

Head of R&D of Google Cloud AI Jia Li has left her position with the company. Li informed Synced in a text message yesterday and the Google team confirmed her departure this morning. An Adjunct Professor at Stanford University's School of Medicine and a widely respected AI researcher, Li told Synced "I'm now pursuing the impact of AI for good in healthcare and working full-time at Stanford University's AIMI (Center for Artificial Intelligence in Medicine & Imaging). In healthcare, I am interested in how AI can improve the outcomes of individual patients as well as hospitals." Chinese media is reporting that Li will start her own AI company with the aim of bringing machine learning solutions to the healthcare industry; and that a number of leading global venture capitals are interested.