In 2015, car-and-rocket man Elon Musk joined with influential startup backer Sam Altman to put artificial intelligence on a new, more open course. They cofounded a research institute called OpenAI to make new AI discoveries and give them away for the common good. Now, the institute's researchers are sufficiently worried by something they built that they won't release it to the public. The AI system that gave its creators pause was designed to learn the patterns of language. It does that very well--scoring better on some reading-comprehension tests than any other automated system.

Recently SoftBank Group launched its latest fund, called Vision Fund 2, which has $108 billion in assets. No doubt, the fund will have a huge impact on the industry. But of course, VCs are not the only ones ramping up their investments. So are mega tech companies. For example, Microsoft has announced a $1 billion equity stake in OpenAI (here's a post I wrote for Forbes.com on the deal).

Some fascinating breakthroughs could make AI technology accessible to many more companies and enterprises. FREMONT, CA: As the influx of structured and unstructured data increases in the conventional ecosystem, the balance between information gathered and information harnessed becomes profoundly dissimilar. However, to reduce the gap between operational and computational knowledge, professionals and experts have started integrating artificial intelligence technology into the functional frameworks. Recently, the industry has seen a considerable effort to fix the "big data issue" of AI. And some exciting breakthroughs have started to arise that could render AI available to many more companies and organizations.

In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network architecture that exploits the relational structure of (P)PDDL planning problems to learn a common set of weights that can be applied to any problem in a domain. By mimicking the actions chosen by a traditional, non-learning planner on a handful of small problems in a domain, ASNets are able to learn a generalised reactive policy that can quickly solve much larger instances from the domain. This work extends the ASNet architecture to make it more expressive, while still remaining invariant to a range of symmetries that exist in PPDDL problems. We also present a thorough experimental evaluation of ASNets, including a comparison with heuristic search planners on seven probabilistic and deterministic domains, an extended evaluation on over 18,000 Blocksworld instances, and an ablation study. Finally, we show that sparsity-inducing regularisation can produce ASNets that are compact enough for humans to understand, yielding insights into how the structure of ASNets allows them to generalise across a domain.

It is a challenging and complex task to acquire information from different regions of a disaster-affected area in a timely fashion. The extensive spread and reach of social media and networks allow people to share information in real-time. However, the processing of social media data and gathering of valuable information require a series of operations such as (1) processing each specific tweet for a text classification, (2) possible location determination of people needing help based on tweets, and (3) priority calculations of rescue tasks based on the classification of tweets. These are three primary challenges in developing an effective rescue scheduling operation using social media data. In this paper, first, we propose a deep learning model combining attention based Bi-directional Long Short-Term Memory (BLSTM) and Convolutional Neural Network (CNN) to classify the tweets under different categories. We use pre-trained crisis word vectors and global vectors for word representation (GLoVe) for capturing semantic meaning from tweets. Next, we perform feature engineering to create an auxiliary feature map which dramatically increases the model accuracy. In our experiments using real data sets from Hurricanes Harvey and Irma, it is observed that our proposed approach performs better compared to other classification methods based on Precision, Recall, F1-score, and Accuracy, and is highly effective to determine the correct priority of a tweet. Furthermore, to evaluate the effectiveness and robustness of the proposed classification model a merged dataset comprises of 4 different datasets from CrisisNLP and another 15 different disasters data from CrisisLex are used. Finally, we develop an adaptive multitask hybrid scheduling algorithm considering resource constraints to perform an effective rescue scheduling operation considering different rescue priorities.

Single-microphone, speaker-independent speech separation is normally performed through two steps: (i) separating the specific speech sources, and (ii) determining the best output-label assignment to find the separation error. The second step is the main obstacle in training neural networks for speech separation. Recently proposed Permutation Invariant Training (PIT) addresses this problem by determining the output-label assignment which minimizes the separation error. In this study, we show that a major drawback of this technique is the overconfident choice of the output-label assignment, especially in the initial steps of training when the network generates unreliable outputs. To solve this problem, we propose Probabilistic PIT (Prob-PIT) which considers the output-label permutation as a discrete latent random variable with a uniform prior distribution. Prob-PIT defines a log-likelihood function based on the prior distributions and the separation errors of all permutations; it trains the speech separation networks by maximizing the log-likelihood function. Prob-PIT can be easily implemented by replacing the minimum function of PIT with a soft-minimum function. We evaluate our approach for speech separation on both TIMIT and CHiME datasets. The results show that the proposed method significantly outperforms PIT in terms of Signal to Distortion Ratio and Signal to Interference Ratio.

Domain adaptation which pays attention to exploiting the knowledge in source domain to promote the learning tasks in target domain plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have achieved significance performance in domain adaptation. However, most existing methods focus on minimizing the distribution divergence by putting the source data and target data together to learn global feature representations, while do not take the local relationship between instances of the same category in different domains into account. To address this problem, we propose a novel Semi-Supervised Representation Learning framework via Dual Autoencoders for domain adaptation, named SSRLDA. More specifically, \textcolor{red}{we extract richer feature representations by learning the global and local feature representations simultaneously using two novel autoencoders}, which are referred to as marginalized denoising autoencoder with adaptation distribution (MDA$_{ad}$) and multi-class marginalized denoising autoencoder (MMDA) respectively. Meanwhile, we \textcolor{red}{adopt an iterative strategy} to make full use of label information to optimize feature representations. Experimental results show that our proposed approach outperforms several state-of-the-art baseline methods.

Capsule networks are constrained by their, relative, inability to deeper in a parameter-inexpensive manner, and also by the general lack of equivariance guarantees. As a step towards bridging these two gaps, we present a new variation of capsule networks termed Space-of-Variation networks (SOVNET). Each layer in SOVNET learns to projectively represent the manifold of legal pose variations for a set of capsules, using learnable neural network - one per capsule-type. Thus, shallower capsules from a local pool predict a deeper capsule by being input into the neural network associated with the type of deeper capsule. In order to capture local object-structures better, benefit from increased parameter-sharing, and have equivariance guarantees; group-equivariant convolutions are used in the prediction mechanism. Further, a new routing algorithm based on the degree-centrality of graph nodes is presented. Experiments on affinely transformed versions of MNIST and FashionMNIST showcase the superiority of SOVNET over certain capsule-network baselines.

Obtaining accurate and reliable images from low-dose computed tomography (CT) is challenging. Regression convolutional neural network (CNN) models that are learned from training data are increasingly gaining attention in low-dose CT reconstruction. This paper modifies the architecture of an iterative regression CNN, BCD-Net, for fast, stable, and accurate low-dose CT reconstruction, and presents the convergence property of the modified BCD-Net. Numerical results with phantom data show that applying faster numerical solvers to model-based image reconstruction (MBIR) modules of BCD-Net leads to faster and more accurate BCD-Net; BCD-Net significantly improves the reconstruction accuracy, compared to the state-of-the-art MBIR method using learned transforms; BCD-Net achieves better image quality, compared to a state-of-the-art iterative NN architecture, ADMM-Net. Numerical results with clinical data show that BCD-Net generalizes significantly better than a state-of-the-art deep (non-iterative) regression NN, FBPConvNet, that lacks MBIR modules.

Enhancing machine capabilities to answer questions has been a topic of considerable focus in recent years of NLP research. Language models like Embeddings from Language Models (ELMo)[1] and Bidirectional Encoder Representations from Transformers (BERT) [2] have been very successful in developing general purpose language models that can be optimized for a large number of downstream language tasks. In this work, we focused on augmenting the pre-trained BERT language model with different output neural net architectures and compared their performance on question answering task posed by the Stanford Question Answering Dataset 2.0 (SQUAD 2.0) [3]. Additionally, we also fine-tuned the pre-trained BERT model parameters to demonstrate its effectiveness in adapting to specialized language tasks. Our best output network, is the contextualized CNN that performs on both the unanswerable and answerable question answering tasks with F1 scores of 75.32 and 64.85 respectively.