Researchers, from biochemists to material scientists, have long relied on the rich variety of organic molecules to solve pressing challenges. Some molecules may be useful in treating diseases, others for lighting our digital displays, still others for pigments, paints, and plastics. The unique properties of each molecule are determined by its structure--that is, by the connectivity of its constituent atoms. Once a promising structure is identified, there remains the difficult task of making the targeted molecule through a sequence of chemical reactions. Organic chemists generally work backwards from the target molecule to the starting materials using a process called retrosynthetic analysis.

If you've spent some time implementing Deep Learning models, you've most likely realized some of the common denominators between any given…

Rather, they're a mashup of bodies, bread and faces twisted grotesquely together and set in a nightmare tent. How did a system so great at generating realistic fake faces go so spectacularly wrong in this scenario? According to Shane's article, it's a vivid (and hilarious) demonstration of what you can and can't do with current deep learning technology. It wasn't a lack of data, since Shane trained the system using 55,000 images from the GBBO. However, the problems started when she introduced faces that were unlike the ones it learned on.

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference, especially when deploying to edge or IoT devices with limited computation capacity and power consumption budget. The uniform bit width quantization across all the layers is usually sub-optimal and the exploration of hybrid quantization for different layers is vital for efficient deep compression. In this paper, we employ the meta learning method to automatically realize low-bit hybrid quantization of neural networks. A MetaQuantNet, together with a Quantization function, are trained to generate the quantized weights for the target DNN. Then, we apply a genetic algorithm to search the best hybrid quantization policy that meets compression constraints. With the best searched quantization policy, we subsequently retrain or finetune to further improve the performance of the quantized target network. Extensive experiments demonstrate the performance of searched hybrid quantization scheme surpass that of uniform bitwidth counterpart. Compared to the existing reinforcement learning (RL) based hybrid quantization search approach that relies on tedious explorations, our meta learning approach is more efficient and effective for any compression requirements since the MetaQuantNet only needs be trained once.

Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval, classification or recommendation can involve tagging or classification based on multiple criteria. In our case, we train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators (actors unknown to our database). Face classifiers are known to be sensitive to label noise. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.

It is becoming evident each and every day that machine learning algorithms are achieving impressive results in domains in which it is hard to specify a set of rules for their procedures. Examples of this phenomenon include industries like finance [49, 5], transportation [37], education [42, 22], health care [23] and tasks like image recognition [41, 16, 17], machine translation [43, 7], and speech recognition [46, 24, 53, 50]. Motivated by the ease of adoption and the increased availability of affordable computational power (especially cloud computing services), machine learning algorithms are being explored in almost every commercial application and are offering great promise for the future of automation. Facing such a vast adoption across multiple disciplines, some of their weaknesses are exposed and sometimes exploited by malicious actors. For example, a common challenge to these algorithms is "generalization" or "robustness", which is the ability of the algorithm to maintain performance whenever dealing with data coming from a different distribution with which it was trained. For a long period of time, the sole focus of machine learning researchers was improving the performance of machine learning systems (true positive rate, accuracy, etc.). Nowadays, the robustness of these systems can no longer be ignored; many of them have been shown to be highly vulnerable to intentional adversarial attacks.

Recent years have witnessed the significant advances of machine learning in a wide spectrum of applications. However, machine learning models, especially deep neural networks, have been recently found to be vulnerable to carefully-crafted input called adversarial samples. The difference between normal and adversarial samples is almost imperceptible to human. Many work have been proposed to study adversarial attack and defense in different scenarios. An intriguing and crucial aspect among those work is to understand the essential cause of model vulnerability, which requires in-depth exploration of another concept in machine learning models, i.e., interpretability. Interpretable machine learning tries to extract human-understandable terms for the working mechanism of models, which also receives a lot of attention from both academia and industry. Recently, an increasing number of work start to incorporate interpretation into the exploration of adversarial robustness. Furthermore, we observe that many previous work of adversarial attacking, although did not mention it explicitly, can be regarded as natural extension of interpretation. In this paper, we review recent work on adversarial attack and defense, particularly, from the perspective of machine learning interpretation. We categorize interpretation into two types, according to whether it focuses on raw features or model components. For each type of interpretation, we elaborate on how it could be used in attacks, or defense against adversaries. After that, we briefly illustrate other possible correlations between the two domains. Finally, we discuss the challenges and future directions along tackling adversary issues with interpretation.

Text-to-image synthesis is the task of generating images from text descriptions. Image generation, by itself, is a challenging task. When we combine image generation and text, we bring complexity to a new level: we need to combine data from two different modalities. Most of recent works in text-to-image synthesis follow a similar approach when it comes to neural architectures. Due to aforementioned difficulties, plus the inherent difficulty of training GANs at high resolutions, most methods have adopted a multi-stage training strategy. In this paper we shift the architectural paradigm currently used in text-to-image methods and show that an effective neural architecture can achieve state-of-the-art performance using a single stage training with a single generator and a single discriminator. We do so by applying deep residual networks along with a novel sentence interpolation strategy that enables learning a smooth conditional space. Finally, our work points a new direction for text-to-image research, which has not experimented with novel neural architectures recently.

Automatic surgical workflow recognition in video is an essentially fundamental yet challenging problem for developing computer-assisted and robotic-assisted surgery. Existing approaches with deep learning have achieved remarkable performance on analysis of surgical videos, however, heavily relying on large-scale labelled datasets. Unfortunately, the annotation is not often available in abundance, because it requires the domain knowledge of surgeons. In this paper, we propose a novel active learning method for cost-effective surgical video analysis. Specifically, we propose a non-local recurrent convolutional network (NL-RCNet), which introduces non-local block to capture the long-range temporal dependency (LRTD) among continuous frames. We then formulate an intra-clip dependency score to represent the overall dependency within this clip. By ranking scores among clips in unlabelled data pool, we select the clips with weak dependencies to annotate, which indicates the most informative ones to better benefit network training. We validate our approach on a large surgical video dataset (Cholec80) by performing surgical workflow recognition task. By using our LRTD based selection strategy, we can outperform other state-of-the-art active learning methods. Using only up to 50% of samples, our approach can exceed the performance of full-data training.

Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed. We consider alternatives to this assumption for the class of goal-directed Reinforcement Learning (RL) problems. Instead of an environment transition model, we assume an imperfect, goal-directed policy. This low-level policy can be improved by a plan, consisting of an appropriate sequence of sub-goals that guide it from the start to the goal state. We propose a planning algorithm, Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS), for approximating the optimal plan by means of proposing intermediate sub-goals which hierarchically partition the initial tasks into simpler ones that are then solved independently and recursively. The algorithm critically makes use of a learned sub-goal proposal for finding appropriate partitions trees of new tasks based on prior experience. Different strategies for learning sub-goal proposals give rise to different planning strategies that strictly generalize sequential planning. We show that this algorithmic flexibility over planning order leads to improved results in navigation tasks in grid-worlds as well as in challenging continuous control environments.