Standard few-shot experiments involve learning to efficiently match unseen samples by class. We claim that few-shot learning should be long term, assimilating knowledge for the future, without forgetting previous concepts. In the mammalian brain, the hippocampus is understood to play a significant role in this process, by learning rapidly and consolidating knowledge to the neocortex incrementally over a short period. In this research we tested whether an artificial hippocampal algorithm (AHA), could be used with a conventional Machine Learning (ML) model that learns incrementally analogous to the neocortex, to achieve one-shot learning both short and long term. The results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting. This study is one of the first examples of using a CLS model of hippocampus to consolidate memories, and it constitutes a step toward few-shot continual learning.

We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs. The network is trained using only local and immediate credit assignment. Despite this constraint, results are comparable to networks trained using deep backpropagation or BackProp Through Time (BPTT). With several examples, we show that the network can associate distant cause and effect in a discrete stochastic process, predict partially-observable higherorder sequences, and learn to generate many time-steps of video simulations. Typical memory consumption is 10-30x less than conventional RNNs, such as LSTM, trained by BPTT. One limitation of the memory is generalization to unseen input sequences. We additionally explore this limitation by measuring next-word prediction perplexity on the Penn Treebank dataset.

Epistatic interactions between genes are believed to be a critical component in the genetic architecture of complex diseases. Genome Wide Association Studies (GWAS) may be able to detect such genetic interactions indirectly, via the identification of associated SNP markers. Major obstacles to progress in this area are: the unknown nature of epistatic interactions, little understanding of the capabilities of different filtering methods, and the computational difficulties for exhaustive analysis. A common platform enabling various detection methods is needed to avoid practical issues such as software compatibility and portability, incompatible input and output formats and varying demands on computational resources. We developed a highly optimised GPU system capable of exhaustively analysing all SNP-pairs in typical GWAS data (0.5M SNPs, 5K samples) in a few minutes on a standard desktop computer. A number of programming elements provided by a functional interface can be used to construct user-defined statistical tests to efficiently score every SNP pair. As a proof of principle, we have implemented 8 methods from the literature via our interface. We have applied all of them using a single GPU to exhaustively scan the 7 popular WTCCC case-control GWAS datasets. We present timing results for these methods, both in their original software implementations and using our platform. Significant improvements in timing are observed, up to 10000 times for CPU implementations of the popular FastEpistasis in PLINK and up to 2 orders of magnitude for some GPU implementations in the literature. As an initial discovery we show plots for overlaps of list of selected pairs by 8 algorithms for Type 2 Diabetes, WTCCC data.

Robust multiple object tracking is the backbone of many higher-level applications such as people counting, behavioral analytics and biomedical imaging. We enhance multiple hypothesis tracker robustness to the problems of split, merge, occlusion and fragment through hierarchical approach. Foreground segmentation and clustered optical flow are used as the first-level tracker input. Only associated track of the first level is fed into the second level with the additional of two virtual measurements. Occlusion predictor is obtained by using the predicted data of each track to distinguish between merge and occlusion. Kalman filter is used to predict and smooth the track's state. Gaussian modelling is used to measure the quality of the hypotheses. Histogram intersection is applied to limit the size expansion of the track. The results show improvement both in terms of accuracy and precision compared to the benchmark trackers [1, 2].

Background One of the limiting factors of current genome-wide association studies (GWAS) is the inability of current methods to comprehensively examine SNP interactions for a reasonable sized dataset. It is hypothesised that this limitation is one of the reasons that GWAS studies have not been able to have a greater impact [1,2]. Many current methods for handling interactions are computationally expensive and do not scale to entire studies. Those methods that do scale often achieve this by pruning their datasets in some manner. This is commonly done by considering only those SNPs that show strong marginal effects, despite the fact that a strongly interacting pair may consist of SNPs with low effects individually.

Odour localisation in an enclosed area is difficult due to the formation of sectors of circulating airflow. Well-defined plumes do not exist, and reactive plume following may not be possible. Odour localisation has been partially achieved in this environment by using knowledge of airflow, and a search that relies on chemical sensing and reasoning. However the results are not specific, with the odour source only restricted to a broad area. This paper presents a solution to the problem by introducing a second search stage using visual sensing. It therefore comprises a bi-modal, two-stage search, with each stage exploiting complementary sensing modalities. This paper presents details of the method and experimental results

We describe a hybrid visuo-spatial topological approach in which global visual localization is triggered at junctions detected in a novel egocentric spatial approximation of the generalized Voronoi diagram. Transited vertices of this GVD are shown empirically to be useful and robust topological features. Visual vertex discrimination is performed without spatial cues, ameliorating junction ambiguity. Several large-scale trials are reported demonstrating fully autonomous exploration and mapping in mixed indoor/outdoor environments