Acquiring a large vocabulary is an important aspect of human intelligence. Onecommon approach for human to populating vocabulary is to learn words duringreading or listening, and then use them in writing or speaking. This ability totransfer from input to output is natural for human, but it is difficult for machines.Human spontaneously performs this knowledge transfer in complicated multimodaltasks, such as Visual Question Answering (VQA). In order to approach human-levelArtificial Intelligence, we hope to equip machines with such ability. Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1.0 dataset in the way that duringtraining, some words appear only in one module (i.e. questions) but not in theother (i.e. answers). In this setting, an intelligent model should understand andlearn the concepts from one module (i.e. questions), and at test time, transfer themto the other (i.e. predict the concepts as answers). We conduct evaluation on thisnew dataset using three existing state-of-the-art VQA neural models. Experimentalresults show a significant drop in performance on this dataset, indicating existingmethods do not address the zero-shot transfer problem. Besides, our analysis findsthat this may be caused by the implicit bias learned during training.

Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation, which we call "CariGANs". It explicitly models geometric exaggeration and appearance stylization using two components: CariGeoGAN, which only models the geometry-to-geometry transformation from face photos to caricatures, and CariStyGAN, which transfers the style appearance from caricatures to face photos without any geometry deformation. In this way, a difficult cross-domain translation problem is decoupled into two easier tasks. The perceptual study shows that caricatures generated by our CariGANs are closer to the hand-drawn ones, and at the same time better persevere the identity, compared to state-of-the-art methods. Moreover, our CariGANs allow users to control the shape exaggeration degree and change the color/texture style by tuning the parameters or giving an example caricature.

One core idea of adversarial example research is to reveal neural network errors under such distribution shift. We show deep networks are not only too sensitive to task-irrelevant changes of their input, as is well-known from -adversarial examples, but are alsotoo invariant to a wide range of task-relevant changes, thus making vast regions in input space vulnerable to adversarial attacks. After identifying this excessive invariance, we propose the usage of bijective deep networks to enable access to all variations. We introduce metameric sampling as an analytic attack for these networks, requiring no optimization, and show that it uncovers large subspaces of misclassified inputs. Then we apply these networks to MNIST and ImageNet and show that one can manipulate the class-specific content of almost any image without changing the hidden activations. Further, we extend the standard cross-entropy loss to strengthen the model against such manipulations via an information-theoretic analysis, providing the first approach tailored explicitly to overcome invariance-based vulnerability. We conclude by empirically illustrating its ability to control undesirable class-specific invariance, showing promise to overcome one major cause for adversarial examples. Figure 1: All images shown cause a competitive ImageNet-trained network to output theexact same probabilities over all 1000 classes (logits shown above each image). The leftmost image is from the ImageNet validation set; all other images are constructed such that they match the non-class related information of images taken from other classes (for details see section 2.2).

This paper addresses the problem of incremental domain adaptation (IDA). We assume each domain comes one after another, and that we could only access data in the current domain. The goal of IDA is to build a unified model performing well on all the domains that we have encountered. We propose to augment a recurrent neural network (RNN) with a directly parameterized memory bank, which is retrieved by an attention mechanism at each step of RNN transition. The memory bank provides a natural way of IDA: when adapting our model to a new domain, we progressively add new slots to the memory bank, which increases the number of parameters, and thus the model capacity. We learn the new memory slots and fine-tune existing parameters by back-propagation. Experimental results show that our approach achieves significantly better performance than fine-tuning alone, which suffers from the catastrophic forgetting problem. Compared with expanding hidden states, our approach is more robust for old domains, shown by both empirical and theoretical results. Our model also outperforms previous work of IDA including elastic weight consolidation (EWC) and the progressive neural network.

This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.

Last year, the Advertising team at The New York Times asked a question: could we accurately predict the emotions that are evoked by Times articles? If so, we could empower advertisers to place ads more relevant to the context in which they are shown. To explore this idea, The Times's Data Science team launched Project Feels, a project to understand and predict the emotional impact of Times articles. In a nutshell, we built prediction algorithms with large amounts of data collected via crowdsourcing. Our predictions made sense qualitatively, and we ran successful experiments demonstrating that readers' emotional response positively correlated with engagement on articles.

It's all a game of construction -- some with a brush, some with a shovel, some choose a pen. I'm an artist, and I've also been building commercial software for a long while. But art and software used to be two parallel tracks in my life; save for the occasional foray into generative art with Processing and computational photography, all my art was analog… until I discovered GANs (Generative Adversarial Networks). Since the invention of GANs in 2014, the machine learning community has produced a number of deep, technical pieces about the technique (such as this one). This is not one of those pieces.

Deep learning has a DRAM problem. Systems designed to do difficult things in real time, such as telling a cat from a kid in a car's backup camera video stream, are continuously shuttling the data that makes up the neural network's guts from memory to the processor. Some systems need four or even eight DRAM chips to sling the 100s of gigabits to the processor, which adds a lot of space and consumes considerable power. Flex Logix says that the interconnect technology and tile-based architecture it developed for reconfigurable chips will lead to AI systems that need the bandwidth of only a single DRAM chip and consume one-tenth the power. Mountain View-based Flex Logix had started to commercialize a new architecture for embedded field programmable gate arrays (eFPGAs). But after some exploration, one of the founders, Cheng C. Wang, realized the technology could speed neural networks.

Subscribe for more (part 3 will be on backpropagation): http://3b1b.co/subscribe Funding provided by Amplify Partners and viewers like you. His post on Neural networks and topology is particular beautiful, but honestly all of the stuff there is great. And if you like that, you'll *love* the publications at distill: https://distill.pub/ For more videos, Welch Labs also has some great series on machine learning: https://youtu.be/i8D90DkCLhI

A recent Sophos study found that almost half (48 per cent) of Australian businesses were hit by ransomware attacks last year, highlighting the need for security vendors to continuously innovate, and more importantly, stay ahead of the cybercriminals. As such, innovative technologies such as artificial intelligence (AI) have become imperative to cybersecurity. There is a misconception that these technologies are the same and can be used interchangeably; while they leverage the same AI principles, machine learning and deep learning are fundamentally different. So what is the difference and how does it work in relation to cyber security? AI is now a widely understood technology, mostly it has been made famous by Hollywood movies (although its application in security does not involve a robot attacking a hacker).