The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE) task. The proposed method, which is inspired by a statistical hypothesis test, consists of two phases: the first phase is to introduce the predictability of textual entailment labels as a null hypothesis which is extremely unacceptable if a target corpus has no hidden bias, and the second phase is to test the null hypothesis using a Naive Bayes model. The experimental result of the Stanford Natural Language Inference (SNLI) corpus does not reject the null hypothesis. Therefore, it indicates that the SNLI corpus has a hidden bias which allows prediction of textual entailment labels from hypothesis sentences even if no context information is given by a premise sentence. This paper also presents the performance impact of NN models for RTE caused by this hidden bias.

We demonstrate that current state-of-the-art approaches to Automated Essay Scoring (AES) are not well-suited to capturing adversarially crafted input of grammatical but incoherent sequences of sentences. We develop a neural model of local coherence that can effectively learn connectedness features between sentences, and propose a framework for integrating and jointly training the local coherence model with a state-of-the-art AES model. We evaluate our approach against a number of baselines and experimentally demonstrate its effectiveness on both the AES task and the task of flagging adversarial input, further contributing to the development of an approach that strengthens the validity of neural essay scoring models.

Working memory is a cognitive process that is responsible for temporarily holding and manipulating information. Most of the empirical neuroscience research on working memory has focused on measuring sustained activity in prefrontal cortex (PFC) and/or parietal cortex during simple delayed-response tasks, and most of the models of working memory have been based on neural integrators. But working memory means much more than just holding a piece of information online. We describe a new theory of working memory, based on a recurrent neural circuit that we call ORGaNICs (Oscillatory Recurrent GAted Neural Integrator Circuits). ORGaNICs are a variety of Long Short Term Memory units (LSTMs), imported from machine learning and artificial intelligence. ORGaNICs can be used to explain the complex dynamics of delay-period activity in prefrontal cortex (PFC) during a working memory task. The theory is analytically tractable so that we can characterize the dynamics, and the theory provides a means for reading out information from the dynamically varying responses at any point in time, in spite of the complex dynamics. ORGaNICs can be implemented with a biophysical (electrical circuit) model of pyramidal cells, combined with shunting inhibition via a thalamocortical loop. Although introduced as a computational theory of working memory, ORGaNICs are also applicable to models of sensory processing, motor preparation and motor control. ORGaNICs offer computational advantages compared to other varieties of LSTMs that are commonly used in AI applications. Consequently, ORGaNICs are a framework for canonical computation in brains and machines.

We propose a technique for multi-task learning from demonstration that trains the controller of a low-cost robotic arm to accomplish several complex picking and placing tasks, as well as non-prehensile manipulation. The controller is a recurrent neural network using raw images as input and generating robot arm trajectories, with the parameters shared across the tasks. The controller also combines VAE-GAN-based reconstruction with autoregressive multimodal action prediction. Our results demonstrate that it is possible to learn complex manipulation tasks, such as picking up a towel, wiping an object, and depositing the towel to its previous position, entirely from raw images with direct behavior cloning. We show that weight sharing and reconstruction-based regularization substantially improve generalization and robustness, and training on multiple tasks simultaneously increases the success rate on all tasks.

Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. The technique improves the resolution and color details of smartphone images so much that they approach the quality of images from laboratory-grade microscopes. The advance could help bring high-quality medical diagnostics into resource-poor regions, where people otherwise do not have access to high-end diagnostic technologies. And the technique uses attachments that can be inexpensively produced with a 3-D printer, at less than $100 a piece, versus the thousands of dollars it would cost to buy laboratory-grade equipment that produces images of similar quality. Cameras on today's smartphones are designed to photograph people and scenery, not to produce high-resolution microscopic images.

SAN FRANCISCO--(BUSINESS WIRE)--The following is an opinion editorial provided by Navin Shenoy, executive vice president and general manager of the Data Center Group at Intel Corporation. In the wide world of big data, artificial intelligence (AI) holds transformational promise. Everything from manufacturing to transportation to retail to education will be improved through its application. But nowhere is that potential more profound than in healthcare, where every one of us has a stake. What if we could predict the next big disease epidemic, and stop it before it kills?

The field of artificial intelligence has spawned a vast range of subset fields and terms: machine learning, neural networks, deep learning and cognitive computing, to name but a few. However here we will turn our attention to the specific term'artificial general intelligence', thanks to the Portland-based AI company Kimera Systems' (momentous) claim to have launched the world's first ever example, called Nigel. The AGI Society defines artificial general intelligence as "an emerging field aiming at the building of "thinking machines"; that is general-purpose systems with intelligence comparable to that of the human mind (and perhaps ultimately well beyond human general intelligence)". AGI would, in theory, be able to perform any intellectual feat a human can. You can now perhaps see why a claim to have launched the world's first ever AGI might be a tad ambitious, to say the least.

This is an implementation of Tensorflow on Spark. The goal of this library is to provide a simple, understandable interface in using Tensorflow on Spark. With SparkFlow, you can easily integrate your deep learning model with a ML Spark Pipeline. Underneath, SparkFlow uses a parameter server to train the Tensorflow network in a distributed manor. Through the api, the user can specify the style of training, whether that is Hogwild or async with locking.

Generative Adversarial Networks (GANs)Generative Adversarial Nets, or GAN, in short, are neural nets which were first introduced by Ian Goodfellow in 2014. The algorithm has been hailed as an important milestone in Deep learning by many AI pioneers. Yann Le Cunn (father of convolutional neural networks) told that GANs is the coolest thing that has happened in deep learning within the last 20 years. Many versions of GAN have since come up like DCGAN, Sequence-GAN, LSTM-GAN, etc. GANs are neural networks composed up of two networks competing with each other. The two networks namely generator -- to generate data set and discriminator -- to validate the data set.

The course combines elements of teaching, coaching and community. For this reason, the batch sizes are small and selective. I will be working with a small/selective group of people to actively transfer their career to AI through education and my network towards specific outcomes/goals. "Great course with many interactions, either group or one to one that helps in the learning. In addition, tailored curriculum to the need of each student and interaction with companies involved in this field makes it even more impactful. As for myself, it allowed me to go into topics of interests that help me in reshaping my career."