Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50% to 80%) is used for training and the rest for validation. In many problems, however, the data is highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesising feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesise data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesising data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, e.g. support vector machine, k-nearest neighbour, deep networks, rule-based classifiers, decision trees, etc. The results demonstrated that: i) a significantly more balanced (and fair) classification results can be achieved; ii) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.

Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an intrinsically driven fashion. This is in contrast to the state-of-the-art reinforcement learning agents, which typically start learning each new task from scratch and struggle with knowledge transfer. In this paper we propose a principled way to learn a basis set of policies, which, when recombined through generalised policy improvement, come with guarantees on the coverage of the final task space. In particular, we concentrate on solving goal-based downstream tasks where the execution order of actions is not important. We demonstrate both theoretically and empirically that learning a small number of policies that reach intrinsically specified goal regions in a disentangled latent space can be re-used to quickly achieve a high level of performance on an exponentially larger number of externally specified, often significantly more complex downstream tasks. Our learning pipeline consists of two stages. First, the agent learns to perform intrinsically generated, goal-based tasks in the total absence of environmental rewards. Second, the agent leverages this experience to quickly achieve a high level of performance on numerous diverse externally specified tasks.

Graph matching plays a central role in such fields as computer vision, pattern recognition, and bioinformatics. Graph matching problems can be cast as two types of quadratic assignment problems (QAPs): Koopmans-Beckmann's QAP or Lawler's QAP. In our paper, we provide a unifying view for these two problems by introducing new rules for array operations in Hilbert spaces. Consequently, Lawler's QAP can be considered as the Koopmans-Beckmann's alignment between two arrays in reproducing kernel Hilbert spaces (RKHS), making it possible to efficiently solve the problem without computing a huge affinity matrix. Furthermore, we develop the entropy-regularized Frank-Wolfe (EnFW) algorithm for optimizing QAPs, which has the same convergence rate as the original FW algorithm while dramatically reducing the computational burden for each outer iteration. We conduct extensive experiments to evaluate our approach, and show that our algorithm significantly outperforms the state-of-the-art in both matching accuracy and scalability.

Analysis of large-scale sequential data has been one of the most crucial tasks in areas such as bioinformatics, text, and audio mining. Existing string kernels, however, either (i) rely on local features of short substructures in the string, which hardly capture long discriminative patterns, (ii) sum over too many substructures, such as all possible subsequences, which leads to diagonal dominance of the kernel matrix, or (iii) rely on non-positive-definite similarity measures derived from the edit distance. Furthermore, while there have been works addressing the computational challenge with respect to the length of string, most of them still experience quadratic complexity in terms of the number of training samples when used in a kernel-based classifier. In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples. To this end, the proposed kernels are explicitly defined through a series of different random feature maps, each corresponding to a distribution of random strings. We show that kernels defined this way are always positive-definite, and exhibit computational benefits as they always produce \emph{Random String Embeddings (RSE)} that can be directly used in any linear classification models. Our extensive experiments on nine benchmark datasets corroborate that RSE achieves better or comparable accuracy in comparison to state-of-the-art baselines, especially with the strings of longer lengths. In addition, we empirically show that RSE scales linearly with the increase of the number and the length of string.

Charge prediction which aims to determine appropriate charges for criminal cases based on textual fact descriptions, is an important technology in the field of AI&Law. Previous works focus on improving prediction accuracy, ignoring the interpretability, which limits the methods' applicability. In this work, we propose a deep neural framework to extract short but charge-decisive text snippets - rationales - from input fact description, as the interpretation of charge prediction. To solve the scarcity problem of rationale annotated corpus, rationales are extracted in a reinforcement style with the only supervision in the form of charge labels. We further propose a dynamic rationale attention mechanism to better utilize the information in extracted rationales and predict the charges. Experimental results show that besides providing charge prediction interpretation, our approach can also capture subtle details to help charge prediction.

Synthetic biology allows us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs. However, traditional synthetic biology approaches involve ad-hoc non systematic engineering practices, which lead to long development times. Here, we present the Automated Recommendation Tool ( ART), a tool that leverages machine learning and probabilistic modeling techniques to guide synthetic biology in a systematic fashion, without the need for a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended strains to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. We demonstrate the capabilities of ART on simulated and real data sets and discuss possible difficulties in achieving satisfactory predictive power. 2 Introduction Metabolic engineering 1 enables us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels 2,3 or anticancer drugs.

This paper proposes a methodology for host-based anomaly detection using a semi-supervised algorithm namely one-class classifier combined with a PCA-based feature extraction technique called Eigentraces on system call trace data. The one-class classification is based on generating a set of artificial data using a reference distribution and combining the target class probability function with artificial class density function to estimate the target class density function through the Bayes formulation. The benchmark dataset, ADFA-LD, is employed for the simulation study. ADFA-LD dataset contains thousands of system call traces collected during various normal and attack processes for the Linux operating system environment. In order to pre-process and to extract features, windowing on the system call trace data followed by the principal component analysis which is named as Eigentraces is implemented. The target class probability function is modeled separately by Radial Basis Function neural network and Random Forest machine learners for performance comparison purposes. The simulation study showed that the proposed intrusion detection system offers high performance for detecting anomalies and normal activities with respect to a set of well-accepted metrics including detection rate, accuracy, and missed and false alarm rates.

Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information Seonwoo Min, 1 Seunghyun Park, 2 Siwon Kim, 1 Hyun-Soo Choi, 1 Sungroh Y oon 1, 3, † 1 Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea 2 Clova AI Research, NA VER Corp., Seongnam 13561, Korea 3 Interdisciplinary Program in Bioinformatics, ASRI, INMC, and ISRC, Seoul National University, Seoul 08826, Korea † Correspondence to: sryoon@snu.ac.kr Abstract A structure of a protein has a direct impact on its properties and functions. However, identification of structural similarity directly from amino acid sequences remains as a challenging problem in computational biology. In this paper, we introduce a novel BERT -wise pre-training scheme for a protein sequence representation model called PLUS, which stands for Protein sequence representations L earned U sing Structural information. As natural language representation models capture syntactic and semantic information of words from a large unlabeled text corpus, PLUS captures structural information of amino acids from a large weakly labeled protein database. Since the Transformer encoder, BERT's original model architecture, has a severe computational requirement to handle long sequences, we first propose to combine a bidirectional recurrent neural network with the BERT -wise pre-training scheme. PLUS is designed to learn protein representations with two pre-training objectives, i.e., masked language modeling and same family prediction. Then, the pre-trained model can be fine-tuned for a wide range of tasks without training randomly initialized task-specific models from scratch. Introduction Proteins consisting of linear chains of amino acids are the most versatile molecules in living organisms. They serve vital functions in almost every biological mechanism, e.g., transmitting nerve pulses, storing and transporting other molecules, and providing immune protection (Berg, Ty-moczko, and Stryer 2006).

Words embedding (distributed word vector representations) have become an essential component of many natural language processing (NLP) tasks such as machine translation, sentiment analysis, word analogy, named entity recognition and word similarity. Despite this, the only work that provides word vectors for Hausa language is that of Bojanowski et al. [1] trained using fastText, consisting of only a few words vectors. This work presents words embedding models using Word2Vec's Continuous Bag of Words (CBoW) and Skip Gram (SG) models. The models, hauWE (Hausa Words Embedding), are bigger and better than the only previous model, making them more useful in NLP tasks. To compare the models, they were used to predict the 10 most similar words to 30 randomly selected Hausa words. hauWE CBoW's 88.7% and hauWE SG's 79.3% prediction accuracy greatly outperformed Bojanowski et al. [1]'s 22.3%.

This paper tackles the goal of conclusion-supplement answer generation for non-factoid questions, which is a critical issue in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI), as users often require supplementary information before accepting a conclusion. The current encoder-decoder framework, however, has difficulty generating such answers, since it may become confused when it tries to learn several different long answers to the same non-factoid question. Our solution, called an ensemble network, goes beyond single short sentences and fuses logically connected conclusion statements and supplementary statements. It extracts the context from the conclusion decoder's output sequence and uses it to create supplementary decoder states on the basis of an attention mechanism. It also assesses the closeness of the question encoder's output sequence and the separate outputs of the conclusion and supplement decoders as well as their combination. As a result, it generates answers that match the questions and have natural-sounding supplementary sequences in line with the context expressed by the conclusion sequence. Evaluations conducted on datasets including "Love Advice" and "Arts & Humanities" categories indicate that our model outputs much more accurate results than the tested baseline models do.