The development of Artificial General Intelligence (AGI) promises to be a major event. Along with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The intention of this paper is to provide an easily accessible and up-to-date collection of references for the emerging field of AGI safety. A significant number of safety problems for AGI have been identified. We list these, and survey recent research on solving them. We also cover works on how best to think of AGI from the limited knowledge we have today, predictions for when AGI will first be created, and what will happen after its creation. Finally, we review the current public policy on AGI.

The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to obtain the same inference capability on a resource-constrained device while providing adaptability to cope with the dynamic changes in the data. We propose AgileNet, a novel lightweight dictionary-based few-shot learning methodology which provides reduced complexity deep neural network for efficient execution at the edge while enabling low-cost updates to capture the dynamics of the new data. Evaluations of state-of-the-art few-shot learning benchmarks demonstrate the superior accuracy of AgileNet compared to prior arts. Additionally, AgileNet is the first few-shot learning approach that prevents model updates by eliminating the knowledge obtained from the primary training. This property is ensured through the dictionaries learned by our novel end-to-end structured decomposition, which also reduces the memory footprint and computation complexity to match the edge device constraints.

Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we propose a recurrent network that is able to discover a notionally unbounded number of topics, analogous to Bayesian non-parametric topic models. Experimental results on the MXM Song Lyrics, 20NewsGroups and Reuters News datasets demonstrate the effectiveness and efficiency of these neural topic models.

After the recent groundbreaking results of AlphaGo, we have seen a strong interest in reinforcement learning in game playing. General Game Playing (GGP) provides a good testbed for reinforcement learning. In GGP, a specification of games rules is given. GGP problems can be solved by reinforcement learning. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex), to allow comparison to Banerjee et al. As expected, Q-learning converges, although much slower than MCTS. Borrowing an idea from MCTS, we enhance Q-learning with Monte Carlo Search, to give QM-learning. This enhancement improves the performance of pure Q-learning. We believe that QM-learning can also be used to improve performance of reinforcement learning further for larger games, something which we will test in future work.

We propose a novel technique for faster Neural Network (NN) training by systematically approximating all the constituent matrix multiplications and convolutions. This approach is complementary to other approximation techniques, requires no changes to the dimensions of the network layers, hence compatible with existing training frameworks. We first analyze the applicability of the existing methods for approximating matrix multiplication to NN training, and extend the most suitable column-row sampling algorithm to approximating multi-channel convolutions. We apply approximate tensor operations to training MLP, CNN and LSTM network architectures on MNIST, CIFAR-100 and Penn Tree Bank datasets and demonstrate 30%-80% reduction in the amount of computations while maintaining little or no impact on the test accuracy. Our promising results encourage further study of general methods for approximating tensor operations and their application to NN training.

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or even fine-tune it with new data. Here, we show that, surprisingly, this is indeed possible. The key observation we make is that the layers of a deep network close to the output layer contain independent, easily extractable class-relevant information that is not contained in the output layer itself. We propose to extract this extra class-relevant information using a simple key-value cache memory to improve the classification performance of the model at test time. Our cache memory is directly inspired by a similar cache model previously proposed for language modeling (Grave et al., 2017). This cache component does not require any training or fine-tuning; it can be applied to any pre-trained model and, by properly setting only two hyper-parameters, leads to significant improvements in its classification performance. Improvements are observed across several architectures and datasets. In the cache component, using features extracted from layers close to the output (but not from the output layer itself) as keys leads to the largest improvements. Concatenating features from multiple layers to form keys can further improve performance over using single-layer features as keys. The cache component also has a regularizing effect, a simple consequence of which is that it substantially increases the robustness of models against adversarial attacks.

The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brain mechanism. At present, most of the theoretical research on deep learning is based on mathematics. This dissertation proposes that the neural network of deep learning is a physical system, examines deep learning from three different perspectives: microscopic, macroscopic, and physical world views, answers multiple theoretical puzzles in deep learning by using physics principles. For example, from the perspective of quantum mechanics and statistical physics, this dissertation presents the calculation methods for convolution calculation, pooling, normalization, and Restricted Boltzmann Machine, as well as the selection of cost functions, explains why deep learning must be deep, what characteristics are learned in deep learning, why Convolutional Neural Networks do not have to be trained layer by layer, and the limitations of deep learning, etc., and proposes the theoretical direction and basis for the further development of deep learning now and in the future. The brilliance of physics flashes in deep learning, we try to establish the deep learning technology based on the scientific theory of physics.

For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit sphere, as opposed to the entire space, and the threshold can be trained in a bounded interval, as opposed to the real line. We show that the NNs in the reduced parameter space are mathematically equivalent to the standard NNs with parameters in the whole space. The reduced parameter space shall facilitate the optimization procedure for the network training, as the search space becomes (much) smaller. We demonstrate the improved training performance using numerical examples.

Neural network optimization is often conceptualized as optimizing parameters, but it is ultimately a matter of optimizing a function defined by inputs and outputs. However, little work has empirically evaluated network optimization in the space of possible functions and much analysis relies on Lipschitz bounds. Here, we measure the behavior of several networks in an $L^2$ Hilbert space. Lipschitz bounds appear reasonable in late optimization but not the beginning. We also observe that the function continues to change even after test error saturates. In light of this we propose a learning rule, Hilbert-constrained gradient descent (HCGD), that regularizes the distance a network can travel through $L^2$-space in any one update. HCGD should increase generalization if it is important that single updates minimally change the output function. Experiments show that HCGD reduces exploration in function space and often, but not always, improves generalization. We connect this idea to the natural gradient, which can also be derived from penalizing changes in the outputs. We conclude that decreased movement in function space is an important consideration in training neural networks.

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the learning procedure. An inappropriate selection can lead to the loss of information of the input during forward propagation and the exponential vanishing/exploding of gradients during back-propagation. Understanding the theoretical properties of untrained random networks is key to identifying which deep networks may be trained successfully as recently demonstrated by Schoenholz et al. (2017) who showed that for deep feedforward neural networks only a specific choice of hyperparameters known as the `edge of chaos' can lead to good performance. We complete these recent results by providing quantitative results showing that, for a class of ReLU-like activation functions, the information propagates indeed deeper when the network is initialized at the edge of chaos. By extending our analysis to a larger class of functions, we then identify an activation function, $\phi_{new}(x) = x \cdot \text{sigmoid}(x)$, which improves the information propagation over ReLU-like functions and does not suffer from the vanishing gradient problem. We demonstrate empirically that this activation function combined to a random initialization on the edge of chaos outperforms standard approaches. This complements recent independent work by Ramachandran et al. (2017) who have observed empirically in extensive simulations that this activation function performs better than many alternatives.