The world seems to be going Artificial Intelligence (AI) crazy! So in this post i thought i would cover the 10 Artificial Intelligence AI Trends highlighted by PwC for 2018. Its about 6 months old now, but the themes are relevant and i wanted to capture (for my own notes) the AI trends in layman terms. This is where a neural network has the ability to learn by engaging with the environment through observations, actions and rewards. DRL is popular type of AI, often used in business applications and gaming – e.g.

More broadly, our work reaffirms the potential of utilising algorithms thought to be used by the brain as inspiration for machine learning architectures. The extensive previous neuroscience research into grid cells makes the agent's interpretability - which is itself a major topic in AI research - significantly easier, by giving us clues about what to look for when trying to understand its internal representations. The work also showcases the potential of using artificial agents actively engaging in complex behaviours within realistic virtual environments to test theories of how the brain works. Taking this principle further, a similar approach could be used to test theories concerning brain areas that are important for perceiving sound or controlling limbs, for example. In the future such networks may well provide a new way for scientists to conduct'experiments', suggesting new theories and even complementing some of the work that is currently conducted in animals.

We have previously discussed a number of introductory topics in natural language processing (NLP), and I had planned at this point to move forward with covering some some useful, practical applications. It then came to my attention that I had overlooked a couple of important introductory discussions which were likely needed prior to moving ahead. The first of those topics is will be covered here, more of a general discussion on the approaches to natural language processing tasks which are common today. This also brings up the question: specifically, what types of NLP tasks are there? The other fundamental topic which has been pointed out to me as being overlooked will be covered next week, and that will be address the common question of "how do we represent text for machine learning systems?"

We examine the relationship between the energy landscape of neural networks and their robustness to adversarial attacks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical evidence that networks corresponding to lower-lying minima in the landscape tend to be more robust. The robustness measure used is the inverse of the sensitivity measure, which we define as the volume of an over-approximation of the reachable set of network outputs under all additive $l_{\infty}$ bounded perturbations on the input data. We present a novel loss function which contains a weighted sensitivity component in addition to the traditional task-oriented and regularization terms. In our experiments on standard machine learning and computer vision datasets (e.g., Iris and MNIST), we show that the proposed loss function leads to networks which reliably optimize the robustness measure as well as other related metrics of adversarial robustness without significant degradation in the classification error.

ABSTRACT In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals. Index Terms-- Source separation, speaker recognition, spectrogram masking, speech recognition 1. INTRODUCTION Recent advances in speech recognition have led to performance improvement in challenging scenarios such as noisy and far-field conditions. However, speech recognition systems still perform poorly when the speaker of interest is recorded in crowded environments, i.e., with interfering speakers in the foreground or background. One way to deal with this issue is to first apply a speech separation system on the noisy audio in order to separate the voices from different speakers.

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties. How can a human train an intelligent agent to understand natural language instructions? We believe that this research question is important from both technological and scientific perspectives. No matter how advanced AI technology becomes, human users may want to customize their intelligent helpers to be able to better understand their desires and needs.

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear counterparts. However, selecting an appropriate activation function is a challenging problem, as it affects the accuracy and the complexity of the given DNN. In this paper, we propose a novel methodology to automatically select the best-possible activation function for each layer of a given DNN, such that the overall DNN accuracy, compared to considering only one type of activation function for the whole DNN, is improved. However, an associated scientific challenge in exploring all the different configurations of activation functions would be time and resource-consuming. Towards this, our methodology identifies the Evaluation Points during learning to evaluate the accuracy in an intermediate step of training and to perform early termination by checking the accuracy gradient of the learning curve. This helps in significantly reducing the exploration time during training. Moreover, our methodology selects, for each layer, the dropout rate that optimizes the accuracy. Experiments show that we are able to achieve on average 7% to 15% Relative Error Reduction on MNIST, CIFAR-10 and CIFAR-100 benchmarks, with limited performance and power penalty on GPUs.

It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what representations do deep neural networks learn. In this work, we move a tiny step towards a theory and better understanding of the representations. Specifically, we study a simpler problem: How similar are the representations learned by two networks with identical architecture but trained from different initializations. We develop a rigorous theory based on the neuron activation subspace match model. The theory gives a complete characterization of the structure of neuron activation subspace matches, where the core concepts are maximum match and simple match which describe the overall and the finest similarity between sets of neurons in two networks respectively. We also propose efficient algorithms to find the maximum match and simple matches. Finally, we conduct extensive experiments using our algorithms. Experimental results suggest that, surprisingly, representations learned by the same convolutional layers of networks trained from different initializations are not as similar as prevalently expected, at least in terms of subspace match.

Designing and modifying complex hull forms for optimal vessel performances have been a major challenge for naval architects. In the present study, Principal Component Analysis (PCA) is introduced to compress the geometric representation of a group of existing vessels, and the resulting principal scores are manipulated to generate a large number of derived hull forms, which are evaluated computationally for their calm-water performances. The results are subsequently used to train a Deep Neural Network (DNN) to accurately establish the relation between different hull forms and their associated performances. Then, based on the fast, parallel DNN-based hull-form evaluation, the large-scale search for optimal hull forms is performed.

Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models. We propose two new statistical tests which are nonparametric, computationally efficient (runtime complexity is linear in the sample size), and interpretable. As a unique advantage, our tests can produce a set of examples (informative features) indicating the regions in the data domain where one model fits significantly better than the other. In a real-world problem of comparing GAN models, the test power of our new test matches that of the state-of-the-art test of relative goodness of fit, while being one order of magnitude faster.