Fact checking today is a reactive process in which journalists wait for a falsehood to begin spreading virally and then publish their final verdict long after the falsehood's spread has tapered off and the damage done. Much of this delay stems from the amount of time and research it takes for fact checkers to investigate a claim and determine its veracity. What if we inverted this process and required every social media post to provide external attribution for its claims and used deep learning algorithms to compare the statements in the post to the original material it cites as its source? Could this "reverse fact checking" largely curb the spread of digital falsehoods? The greatest limitation of today's fact checking landscape is the time and effort it takes fact checkers to investigate a claim.

They have reached the point where they learn by themselves and make their own decisions. The consequences can be downright freaky. There are machines that dream, read words in people's brains, and evolve themselves into art masters. The darker skills are enough to make anyone wear an anti-AI device, which is being developed. Some AI systems show signs of mental illness and prejudice, while others are too dangerous for release to the public. In 2019, a video was released on YouTube.

Generative Adversarial Networks (GAN) shook up the deep learning world. When they first appeared in 2014, they proposed a new and fresh approach to modeling and gave a possibility for new neural network architectures to emerge. Since standard GAN architecture is composed from two neural networks, we can play around and use different approaches for those networks and thus create new and shiny architectures. The idea is to make an appropriate model for your problem and generate data which can be used in a real-world business scenario. So far, we had a chance to see how to implement the standard GAN and Deep Convolutional GAN (combining CNN concepts with GAN concepts), but the zoo of GAN architectures grows on a daily basis.

With rapidly scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency. This work aims to advance the compression beyond the weights to neuron activations. We propose an end-to-end Joint Pruning (JP) technique which integrates the activation pruning with the weight pruning. By distinguishing and taking on the different significance of neuron responses and connections during learning, the generated network, namely JPnet, optimizes the sparsity of activations and weights for improving execution efficiency. To our best knowledge, JP is the first technique that simultaneously explores the redundancy in both weights and activations. The derived deep sparsification in the JPnet reveals more optimizing potentialities for the existing DNN accelerators dedicated for sparse matrix operations. The effectiveness of JP technique is thoroughly evaluated through various network models with different activation functions and on different datasets. With $<0.4\%$ degradation on testing accuracy, a JPnet can save $71.1\% \sim 96.35\%$ of computation cost, compared to the original dense models with up to $5.8\times$ and $10\times$ reductions in activation and weight numbers, respectively. Compared to state-of-the-art weight pruning technique, JPnet can further reduce the computation cost $1.2\times \sim 2.7\times$.

The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of automated methods for neural architecture search. The choice of the network architecture has proven to be critical, and many advances in deep learning spring from its immediate improvements. However, deep learning techniques are computationally intensive and their application requires a high level of domain knowledge. Therefore, even partial automation of this process helps to make deep learning more accessible to both researchers and practitioners. With this survey, we provide a formalism which unifies and categorizes the landscape of existing methods along with a detailed analysis that compares and contrasts the different approaches. We achieve this via a comprehensive discussion of the commonly adopted architecture search spaces and architecture optimization algorithms based on principles of reinforcement learning and evolutionary algorithms along with approaches that incorporate surrogate and one-shot models. Additionally, we address the new research directions which include constrained and multi-objective architecture search as well as automated data augmentation, optimizer and activation function search.

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. The watermark allows the legitimate owner to detect copyright violations of their model. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and show that an adversary can remove the watermark fully by just relying on public data and without any access to the model's sensitive information such as the training data set, the trigger set or the model parameters. We as well prove the security inadequacy of the backdoor-based watermarking in keeping the watermark hidden by proposing an attack that detects whether a model contains a watermark.

The distributed learning could be monitored by a centralized certification authority which Deep learning algorithms, such as deep convolutional would be in charge of the validation of each iteration of the neural networks (CNN) [1], are efficient tools to help data learning process. Alternatively, a blockchain could be used scientists process the huge amounts of potentially very sensitive to store auditable records of each and every transaction on data generated e.g. in medical, financial or industrial an immutable decentralized ledger. This approach has been applications (including data generated from smart sensors suggested in [7], where it is advocated that blockchains can such as smart meters and other IoT sensors for smart cities be used to store signatures of patient records.

Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature. The resulting approach, called CNAPs, comprises a classifier whose parameters are modulated by an adaptation network that takes the current task's dataset as input. We demonstrate that CNAPs achieves state-of-the-art results on the challenging Meta-Dataset benchmark indicating high-quality transfer-learning. We show that the approach is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPs is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, we show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and analyze the interaction between attention and syntax over a large corpus. We find that attention targets different parts of speech at different layer depths within the model, and that attention aligns with dependency relations most strongly in the middle layers. We also find that the deepest layers of the model capture the most distant relationships. Finally, we extract exemplar sentences that reveal highly specific patterns targeted by particular attention heads.