The retrosplenial cortex is involved in spatial memory function, but the contribution of its individual areas is not well known. To elucidate the involvement of retrosplenial cortical areas 29c and 30 in spatial memory, we analyzed the expression of c-Fos in these areas in the experimental group of rats that were trained in a spatial place avoidance task, i.e. to avoid shocks presented in an un...

Recent reports have raised concerns about the ability of long-term potentiation (LTP) to account for associative learning and memory. In this paper, we review the many mechanistic similarities between one form of associative learning, Pavlovian fear conditioning, and amygdaloid LTP. We then address many of the criticisms levied against LTP within the framework of fear conditioning. We believe t...

Code flaws or vulnerabilities are prevalent in software systems and can potentially cause a variety of problems including deadlock, information loss, or system failure. A variety of approaches have been developed to try and detect the most likely locations of such code vulnerabilities in large code bases. Most of them rely on manually designing features (e.g. complexity metrics or frequencies o...

Time series data constitutes a distinct and growing problem in machine learning. As the corpus of time series data grows larger, deep models that simultaneously learn features and classify with these features can be intractable or suboptimal. In this paper, we present feature learning via long short term memory (LSTM) networks and prediction via gradient boosting trees (XGB). Focusing on the co...

Named Entity Recognition (NER) is important in analysing the context of a statement and also the sentiments associated with it. Although Twitter Data is noisy, it is valuable due to the amount of information it can provide. Therefore, NER for Twitter Data is necessary. Our model aims to extract the named entities from tweets using a Recurrent Neural Network Core. Long Short Term Memory (LSTM) w...

A long line of research has studied the power of conflictdriven clause learning (CDCL) and how it compares to the resolution proof system in which it searches for proofs. It has been shown that CDCL can polynomially simulate resolution even with an adversarially chosen learning scheme as long as it is asserting. However, the simulation only works under the assumption that no learned clauses are...

Learning to navigate in 3D environments from raw sensory input is an important step towards bridging the gap between human players and artificial intelligence in digital games. Recent advances in deep reinforcement learning have seen success in teaching agents to play Atari 2600 games from raw pixel information where the environment is always fully observable by the agent. This is not true for ...

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing learned latent codes with more semantic information and better generalization....

Background and Objectives: Students with learning difficulties encounter poorer school outcomes and major problems in learning. Researchers investigated the factors in preschool stage that will help to diagnosis learning problems.  Methods: A meta-analytic review provides means for assessing which factors show the strongest effects on long-term outcomes. Results: This article presents a ...