Recurrent neural networks are very popular and effective at solving difficult sequence problems such as language translation, creation of artificial music, and video prediction. New architectures, such as Sequence to Sequences networks by Sutskever et al. (2014) and Memory Networks by Sukhbaatar et al. (2015) are used to solve problems in language translation and answer questions using a large memory bank. However, these problems generally have training data with given sequence outputs (for example, a model translating a sentence from English to 1 Spanish). Because input and output sequences are known a priori for these problems, it is possible to solve them with a fixed model architecture. A fixed model architecture is effective for sequences, but there are a number of problems related to multiple time series datasets that do not have a natural sequence size.

Generating sequential decision process from huge amounts of measured process data is a future research direction for collaborative factory automation, making full use of those online or offline process data to directly design flexible make decisions policy, and evaluate performance. The key challenges for the sequential decision process is to online generate sequential decision-making policy directly, and transferring knowledge across tasks domain. Most multi-task policy generating algorithms often suffer from insufficient generating cross-task sharing structure at discrete-time nonlinear systems with applications. This paper proposes the multi-task generative adversarial nets with shared memory for cross-domain coordination control, which can generate sequential decision policy directly from raw sensory input of all of tasks, and online evaluate performance of system actions in discrete-time nonlinear systems. Experiments have been undertaken using a professional flexible manufacturing testbed deployed within a smart factory of Weichai Power in China. Results on three groups of discrete-time nonlinear control tasks show that our proposed model can availably improve the performance of task with the help of other related tasks.

Though deep neural networks have great success in natural language processing, they are limited at more knowledge intensive AI tasks, such as open-domain Question Answering (QA). Existing end-to-end deep QA models need to process the entire text after observing the question, and therefore their complexity in responding a question is linear in the text size. This is prohibitive for practical tasks such as QA from Wikipedia, a novel, or the Web. We propose to solve this scalability issue by using symbolic meaning representations, which can be indexed and retrieved efficiently with complexity that is independent of the text size. We apply our approach, called the N-Gram Machine (NGM), to three representative tasks. First as proof-of-concept, we demonstrate that NGM successfully solves the bAbI tasks of synthetic text. Second, we show that NGM scales to large corpus by experimenting on "life-long bAbI", a special version of bAbI that contains millions of sentences. Lastly on the WikiMovies dataset, we use NGM to induce latent structure (i.e. schema) and answer questions from natural language Wikipedia text, with only QA pairs as weak supervision.

We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.

This paper proposes a first order gradient reinforcement learning algorithm, which can be seen as a variant for Trust Region Policy Optimization(TRPO). This method, which we call policy optimization with penalized point probability distance (POP3D), keeps almost all positive spheres of proximal policy optimization (PPO) such as easy implementation, fast learning and high score capability. As PPO, we also use a single surrogate objective without constraints, where a penalized item based on point probability distance is included to prevent update step from growing too large. Experiments verify that POP3D is state-of-the-art within 40 million frame steps on 49 Atari games based on two common metrics, which can be a competitive alternative to PPO. Moreover, comparison experiments regarding PPO based on Mujoco environment verify that POP3D is also competitive in continuous domain. In addition, we release the code on github https://github.com/cxxgtxy/POP3D.git.

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks is still large. Current adversarial training strategies improve the robustness against adversarial samples. However, these methods lead to accuracy reduction when the input examples are clean thus hinders the practicability. In this paper, we investigate an approach that protects the neural network classification from the adversarial samples and improves its accuracy when the input examples are clean. We demonstrate the versatility and effectiveness of our proposed approach on a variety of different networks and datasets.

Deep reinforcement learning has led to several recent breakthroughs, though the learned policies are often based on black-box neural networks. This makes them difficult to interpret and to impose desired specification constraints during learning. We present an iterative framework, MORL, for improving the learned policies using program synthesis. Concretely, we propose to use synthesis techniques to obtain a symbolic representation of the learned policy, which can then be debugged manually or automatically using program repair. After the repair step, we use behavior cloning to obtain the policy corresponding to the repaired program, which is then further improved using gradient descent. This process continues until the learned policy satisfies desired constraints. We instantiate MORL for the simple CartPole problem and show that the programmatic representation allows for high-level modifications that in turn lead to improved learning of the policies.

Researchers from the Tokyo Institute of Technology used an artificial intelligence program termed a Convolutional Neural Network. Applying this technology the researchers demonstrated how artificial intelligence can be trained to catalog and analyze volcanic ash particle shapes. The significance is that as the form and shape of volcanic particles are connected to the type of volcanic eruption, this systematic approach can assist scientists in providing information on eruptions. Such insights can aid volcanic hazard mitigation efforts. In machine learning, a convolutional neural network is a type of deep, feed-forward artificial neural network. This form of artificial intelligence is best equipped for analyzing visual imagery.

Artificial Intelligence (AI) is a broad term for technologies that imitate human intelligence. It covers a range of techniques such as voice and image recognition, machine learning techniques and semantic search. Machine Learning Techniques use algorithms to learn from past data, and create predictive models. Other AI applications do the work of human operators. Marketing has been under pressure since the time rapid technological development disrupted marketing as it was traditionally practiced.