Artificial Intelligence (AI) is a branch of computer science that helps build smart machines. AI provides data that makes these machines capable enough to match human intelligence. As a result, many industries have taken advantage of AI technologies. Machine Learning and Deep Learning are the two subsets of Artificial Intelligence. Whereas machine learning refers to computers able to think and act with less human intervention, deep learning involves computers able to use structures modeled on the human brain.

This week, we launched our new series of interviews with brilliant women working in the critical space of AI Ethics and discuss their groundbreaking work. Our first 6 episodes are sponsored by IBM…

Over the last decade, neural networks have become a trendy topic, ranging from image recognition to text generation and even video gameplay applications. On the other hand, these artificial neural networks are just mounds of math inside a computer. While they are capable of tremendous things, the technology has yet to demonstrate the ability to develop actual intelligence. Researchers at Cortical Labs, Australia propose that integrating neurons into digital systems to tap on their inherent intelligence could enable performance that would be impossible to achieve with silicon alone and provide insight into the biological origins of intelligence. The overall goal of the research is to use biological neurons' processing capability to build "synthetic biological intelligence."

We consider Bayesian optimization of expensive-to-evaluate experiments that generate vector-valued outcomes over which a decision-maker (DM) has preferences. These preferences are encoded by a utility function that is not known in closed form but can be estimated by asking the DM to express preferences over pairs of outcome vectors. To address this problem, we develop Bayesian optimization with preference exploration, a novel framework that alternates between interactive real-time preference learning with the DM via pairwise comparisons between outcomes, and Bayesian optimization with a learned compositional model of DM utility and outcomes. Within this framework, we propose preference exploration strategies specifically designed for this task, and demonstrate their performance via extensive simulation studies.

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix token parameters for each downstream task. Despite being lightweight and modular, prefix-tuning still lacks robustness to textual adversarial attacks. However, most currently developed defense techniques necessitate auxiliary model update and storage, which inevitably hamper the modularity and low storage of prefix-tuning. In this work, we propose a robust prefix-tuning framework that preserves the efficiency and modularity of prefix-tuning. The core idea of our framework is leveraging the layerwise activations of the language model by correctly-classified training data as the standard for additional prefix finetuning. During the test phase, an extra batch-level prefix is tuned for each batch and added to the original prefix for robustness enhancement. Extensive experiments on three text classification benchmarks show that our framework substantially improves robustness over several strong baselines against five textual attacks of different types while maintaining comparable accuracy on clean texts. We also interpret our robust prefix-tuning framework from the optimal control perspective and pose several directions for future research.

In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing method for training data in Neural Machine Translation. Among them, BPE/BPE-dropout is one of the fastest and most effective method compared to conventional approaches. However, compression-based approach has a drawback in that generating multiple segmentations is difficult due to the determinism. To overcome this difficulty, we focus on a probabilistic string algorithm, called locally-consistent parsing (LCP), that has been applied to achieve optimum compression. Employing the probabilistic mechanism of LCP, we propose LCP-dropout for multiple subword segmentation that improves BPE/BPE-dropout, and show that it outperforms various baselines in learning from especially small training data.

This paper stresses the importance of biases in the field of artificial intelligence (AI) in two regards. First, in order to foster efficient algorithmic decision-making in complex, unstable, and uncertain real-world environments, we argue for the structurewise implementation of human cognitive biases in learning algorithms. Secondly, we argue that in order to achieve ethical machine behavior, filter mechanisms have to be applied for selecting biased training stimuli that represent social or behavioral traits that are ethically desirable. We use insights from cognitive science as well as ethics and apply them to the AI field, combining theoretical considerations with seven case studies depicting tangible bias implementation scenarios. Ultimately, this paper is the first tentative step to explicitly pursue the idea of a re-evaluation of the ethical significance of machine biases, as well as putting the idea forth to implement cognitive biases into machines.

Everyone wants to write beautiful and correct text, yet the lack of language skills, experience, or hasty typing can result in errors. By employing the recent advances in transformer architectures, we construct a grammatical error correction model for Lithuanian, the language rich in archaic features. We compare subword and byte-level approaches and share our best trained model, achieving F$_{0.5}$=0.92, and accompanying code, in an online open-source repository.

Expectation-Maximization (EM) algorithm is a popular choice for learning latent variable models. Variants of the EM have been initially introduced by Neal and Hinton (1998), using incremental updates to scale to large datasets, and by Wei and Tanner (1990); Delyon et al. (1999), using Monte Carlo (MC) approximations to bypass the intractable conditional expectation of the latent data for most nonconvex models. In this paper, we propose a general class of methods called Two-Timescale EM Methods based on a two-stage approach of stochastic updates to tackle an essential nonconvex optimization task for latent variable models. We motivate the choice of a double dynamic by invoking the variance reduction virtue of each stage of the method on both sources of noise: the index sampling for the incremental update and the MC approximation. We establish finite-time and global convergence bounds for nonconvex objective functions. Numerical applications on various models such as deformable template for image analysis or nonlinear models for pharmacokinetics are also presented to illustrate our findings.

In recent years, many works have investigated the feasibility of conversational robots for performing specific tasks, such as healthcare and interview. Along with this development comes a practical issue: how should we synthesize robotic voices to meet the needs of different situations? In this paper, we discuss this issue from three perspectives: 1) the difficulties of synthesizing non-verbal and interaction-oriented speech signals, particularly backchannels; 2) the scenario classification for robotic voice synthesis; 3) the ethical issues regarding the design of robot voice for its emotion and identity. We present the findings of relevant literature and our prior work, trying to bring the attention of human-robot interaction researchers to design better conversational robots in the future.