In reinforcement learning, universal successor features (SFs) are a way to provide zero-shot adaptation to new tasks at test time: they provide optimal policies for all downstream reward functions lying in the linear span of a set of base features. But it is unclear what constitutes a good set of base features, that could be useful for a wide set of downstream tasks beyond their linear span. Laplacian eigenfunctions (the eigenfunctions of $\Delta+\Delta^\ast$ with $\Delta$ the Laplacian operator of some reference policy and $\Delta^\ast$ that of the time-reversed dynamics) have been argued to play a role, and offer good empirical performance. Here, for the first time, we identify the optimal base features based on an objective criterion of downstream performance, in a non-tautological way without assuming the downstream tasks are linear in the features. We do this for three generic classes of downstream tasks: reaching a random goal state, dense random Gaussian rewards, and random ``scattered'' sparse rewards. The features yielding optimal expected downstream performance turn out to be the \emph{same} for these three task families. They do not coincide with Laplacian eigenfunctions in general, though they can be expressed from $\Delta$: in the simplest case (deterministic environment and decay factor $\gamma$ close to $1$), they are the eigenfunctions of $\Delta^{-1}+(\Delta^{-1})^\ast$. We obtain these results under an assumption of large behavior cloning regularization with respect to a reference policy, a setting often used for offline RL. Along the way, we get new insights into KL-regularized\option{natural} policy gradient, and into the lack of SF information in the norm of Bellman gaps.

Chronic pain significantly diminishes the quality of life for millions worldwide. While psychoeducation and therapy can improve pain outcomes, many individuals experiencing pain lack access to evidence-based treatments or fail to complete the necessary number of sessions to achieve benefit. Reinforcement learning (RL) shows potential in tailoring personalized pain management interventions according to patients' individual needs while ensuring the efficient use of scarce clinical resources. However, clinicians, patients, and healthcare decision-makers are concerned that RL solutions could exacerbate disparities associated with patient characteristics like race or gender. In this article, we study gender fairness in personalized pain care recommendations using a real-world application of reinforcement learning (Piette et al., 2022a). Here, adhering to gender fairness translates to minimal or no disparity in the utility received by subpopulations as defined by gender. We investigate whether the selection of relevant patient information (referred to as features) used to assist decision-making affects gender fairness. Our experiments, conducted using real-world data (Piette, 2022), indicate that included features can impact gender fairness. Moreover, we propose an RL solution, NestedRecommendation, that demonstrates the ability: i) to adaptively learn to select the features that optimize for utility and fairness, and ii) to accelerate feature selection and in turn, improve pain care recommendations from early on, by leveraging clinicians' domain expertise.

This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm (GA). The OFR reshapes the input space improving the conditioning of the gradient-based algorithm used for the training. Moreover, the scale factors exploration entailed by GA trials and selection corresponds to different initialization of the first layer weights at each training attempt, thus realizing a multi-start global search algorithm (even though restrained to few weights only) which fosters the achievement of a global minimum. The approach has been tested on a FFNN modeling the outcome of a real industrial process (centerless grinding).

Random Forest is a machine learning method that offers many advantages, including the ability to easily measure variable importance. Class balancing technique is a well-known solution to deal with class imbalance problem. However, it has not been actively studied on RF variable importance. In this paper, we study the effect of class balancing on RF variable importance. Our simulation results show that over-sampling is effective in correctly measuring variable importance in class imbalanced situations with small sample size, while under-sampling fails to differentiate important and non-informative variables. We then propose a variable selection algorithm that utilizes RF variable importance and its confidence interval. Through an experimental study using many real and artificial datasets, we demonstrate that our proposed algorithm efficiently selects an optimal feature set, leading to improved prediction performance in class imbalance problem.

This paper proposes a cross-lingual classification method for English, Korean, and Tamil, which employs both language-independent features and language-unique features. First, we extract thirty-nine features from diverse speech dimensions such as voice quality, pronunciation, and prosody. Second, feature selections are applied to identify the optimal feature set for each language. A set of shared features and a set of distinctive features are distinguished by comparing the feature selection results of the three languages. Lastly, automatic severity classification is performed, utilizing the two feature sets. Notably, the proposed method removes different features by languages to prevent the negative effect of unique features for other languages. Accordingly, eXtreme Gradient Boosting (XGBoost) algorithm is employed for classification, due to its strength in imputing missing data. In order to validate the effectiveness of our proposed method, two baseline experiments are conducted: experiments using the intersection set of mono-lingual feature sets (Intersection) and experiments using the union set of mono-lingual feature sets (Union). According to the experimental results, our method achieves better performance with a 67.14% F1 score, compared to 64.52% for the Intersection experiment and 66.74% for the Union experiment. Further, the proposed method attains better performances than mono-lingual classifications for all three languages, achieving 17.67%, 2.28%, 7.79% relative percentage increases for English, Korean, and Tamil, respectively. The result specifies that commonly shared features and language-specific features must be considered separately for cross-language dysarthria severity classification.

This short paper describes an ongoing research project that requires the automated self-play learning and evaluation of a large number of board games in digital form. We describe the approach we are taking to determine relevant features, for biasing MCTS playouts for arbitrary games played on arbitrary geometries. Benefits of our approach include efficient implementation, the potential to transfer learnt knowledge to new contexts, and the potential to explain strategic knowledge embedded in features in human-comprehensible terms.

We propose a novel sparse spectrum approximation of Gaussian process (GP) tailored for Bayesian optimisation. Whilst the current sparse spectrum methods provide good approximations for regression problems, it is observed that this particular form of sparse approximations generates an overconfident GP, i.e. it predicts less variance than the original GP. Since the balance between predictive mean and the predictive variance is a key determinant in the success of Bayesian optimisation, the current sparse spectrum methods are less suitable. We derive a regularised marginal likelihood for finding the optimal frequencies in optimisation problems. The regulariser trades the accuracy in the model fitting with the targeted increase in the variance of the resultant GP. We first consider the entropy of the distribution over the maxima as the regulariser that needs to be maximised. Later we show that the Expected Improvement acquisition function can also be used as a proxy for that, thus making the optimisation less computationally expensive. Experiments show an increase in the Bayesian optimisation convergence rate over the vanilla sparse spectrum method.

Long non-coding RNAs (lncRNAs) are a class of non-coding RNAs which play a significant role in several biological processes. RNA-seq based transcriptome sequencing has been extensively used for identification of lncRNAs. However, accurate identification of lncRNAs in RNA-seq datasets is crucial for exploring their characteristic functions in the genome as most coding potential computation (CPC) tools fail to accurately identify them in transcriptomic data. Well-known CPC tools such as CPC2, lncScore, CPAT are primarily designed for prediction of lncRNAs based on the GENCODE, NONCODE and CANTATAdb databases. The prediction accuracy of these tools often drops when tested on transcriptomic datasets. This leads to higher false positive results and inaccuracy in the function annotation process. In this study, we present a novel tool, PLIT, for the identification of lncRNAs in plants RNA-seq datasets. PLIT implements a feature selection method based on L1 regularization and iterative Random Forests (iRF) classification for selection of optimal features. Based on sequence and codon-bias features, it classifies the RNA-seq derived FASTA sequences into coding or long non-coding transcripts. Using L1 regularization, 31 optimal features were obtained based on lncRNA and protein-coding transcripts from 8 plant species. The performance of the tool was evaluated on 7 plant RNA-seq datasets using 10-fold cross-validation. The analysis exhibited superior accuracy when evaluated against currently available state-of-the-art CPC tools.

Deep learning is a concept that most people know is valuable but do not understand. Global industries, however, are seeing it's worth and investing heavily in the technology; the global deep learning market is expected to reach $10.2 billion by 2025. What are the nuances and intricacies that make deep learning a practical solution to some of today's most complex problems? And how can this technology be understood by more, making it a less intimidating and more approachable topic? "One reason why deep learning is a confusing concept to many is that it is often used alongside the terms machine learning (ML) and artificial intelligence (AI). Deep learning (DL) is a subset of ML, which is itself a subset of AI," explains Jennifer Roubaud, the VP of UK and Ireland for Dataiku.

Electroencephalogram, an influential equipment for analyzing humans activities and recognition of seizure attacks can play a crucial role in designing accurate systems which can distinguish ictal seizures from regular brain alertness, since it is the first step towards accomplishing a high accuracy computer aided diagnosis system (CAD). In this article a novel approach for classification of ictal signals with wavelet based cross frequency coupling (CFC) is suggested. After extracting features by wavelet based CFC, optimal features have been selected by t-test and quadratic discriminant analysis (QDA) have completed the Classification.