Idealised as universal approximators, learners such as neural networks can be viewed as "variable functions" that may become one of a range of concrete functions after training. In the same way that equations constrain the possible values of variables in algebra, we may view objective functions as constraints on the behaviour of learners. We extract the equivalences perfectly optimised objective functions impose, calling them "tasks". For these tasks, we develop a formal graphical language that allows us to: (1) separate the core tasks of a behaviour from its implementation details; (2) reason about and design behaviours model-agnostically; and (3) simply describe and unify approaches in machine learning across domains. As proof-of-concept, we design a novel task that enables converting classifiers into generative models we call "manipulators", which we implement by directly translating task specifications into code. The resulting models exhibit capabilities such as style transfer and interpretable latent-space editing, without the need for custom architectures, adversarial training or random sampling. We formally relate the behaviour of manipulators to GANs, and empirically demonstrate their competitive performance with VAEs. We report on experiments across vision and language domains aiming to characterise manipulators as approximate Bayesian inversions of discriminative classifiers.

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality reduction methods may struggle with nonlinear data, unsupervised deep learning models such as autoencoders can model non-linear relationships. Stacked autoencoders feature multiple interconnected layers to capture hierarchical data representations useful for remote sensing data. This study presents an unsupervised machine learning-based framework for processing remote sensing data using stacked autoencoders for dimensionality reduction and k-means clustering for mapping geological units. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Western New South Wales, Australia. We also compare stacked autoencoders with principal component analysis and canonical autoencoders. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units. We find that the accuracy of stacked autoencoders ranges from 86.6 % to 90 %, depending on the remote sensing data type, which is superior to their counterparts. We also find that the generated maps align with prior geological knowledge of the study area while providing novel insights into geological structures.

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and related tasks, the representations have mostly ignored factors of speech that are encoded at coarser level, like characteristics of the speaker or channel that remain consistent through-out a speech utterance. In this work, we propose a framework for Learning Disentangled Self Supervised (termed as Learn2Diss) representations of speech, which consists of frame-level and an utterance-level encoder modules. The two encoders are initially learned independently, where the frame-level model is inspired by existing self supervision techniques, thereby learning pseudo-phonemic representations, while the utterance-level encoder is inspired by constrastive learning of pooled embeddings, thereby learning pseudospeaker representations. The joint learning of these two modules consists of disentangling the two encoders using a mutual information based criterion. With several downstream evaluation experiments, we show that the proposed Learn2Diss framework achieves state-of-the-art results on a variety of tasks, with the framelevel encoder representations improving semantic tasks, while the utterance-level representations improve non-semantic tasks.

We applied machine learning to the unmet medical need of rapid and accurate diagnosis and prognosis of acute infections and sepsis in emergency departments. Our solution consists of a Myrna (TM) Instrument and embedded TriVerity (TM) classifiers. The instrument measures abundances of 29 messenger RNAs in patient's blood, subsequently used as features for machine learning. The classifiers convert the input features to an intuitive test report comprising the separate likelihoods of (1) a bacterial infection (2) a viral infection, and (3) severity (need for Intensive Care Unit-level care). In internal validation, the system achieved AUROC = 0.83 on the three-class disease diagnosis (bacterial, viral, or non-infected) and AUROC = 0.77 on binary prognosis of disease severity. The Myrna, TriVerity system was granted breakthrough device designation by the United States Food and Drug Administration (FDA). This engineering manuscript teaches the standard and novel machine learning methods used to translate an academic research concept to a clinical product aimed at improving patient care, and discusses lessons learned.

We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either in the case of the training loss (finite samples) or the population one (online setting). A key qualitative feature of the dynamics is the existence of a perfect interpolator of the data, irrespective of the sample size. In both scenarios, we provide precise, non-asymptotic rates of convergence to the (possibly degenerate) stationary distribution. Additionally, we describe this asymptotic distribution, offering estimates of its mean, deviations from it, and a proof of the emergence of heavy-tails related to the step-size magnitude. Numerical simulations supporting our findings are also presented.

We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, out method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive experiments on language and vision tasks (e.g. GPT and ResNet) to showcase that GeN optimizers match the state-of-the-art performance, which was achieved with carefully tuned learning rate schedulers. Code to be released at \url{https://github.com/ShiyunXu/AutoGeN}.

GPR models can also incorporate prior knowledge through selecting an appropriate kernel function. GPR commonly assumes a homoscedastic Gaussian distribution for observation noise because this yields an analytical form for the posterior predictive prediction. However, Bayesian inference based on Gaussian noise distributions is known to be sensitive to outliers which are defined as observations that strongly deviate from model assumptions. In regression, outliers can arise from relevant inputs being absent from the model, measurement error, and other unknown sources. These outliers are associated with unconsidered sources of variation that affect the target variable sporadically. In this case, the observation model is unable to distinguish between random noise and systematic effects not captured by the model. In the context of GPR under Gaussian noise, outliers can heavily influence the posterior predictive distribution, resulting in a biased estimate of the mean function and overly confident prediction intervals. Therefore, robust observation models are desired in the presence of potential outliers.

The avalanche of AI deployment and its security-privacy concerns are two sides of the same coin. Article 17 of GDPR calls for the Right to Erasure; data has to be obliterated from a system to prevent its compromise. Extant research in this aspect focuses on effacing sensitive data attributes. However, several passive modes of data compromise are yet to be recognized and redressed. The embedding of footprints of training data in a prediction model is one such facet; the difference in performance quality in test and training data causes passive identification of data that have trained the model. This research focuses on addressing the vulnerability arising from the data footprints. The three main aspects are -- i] exploring the vulnerabilities of different classifiers (to segregate the vulnerable and the non-vulnerable ones), ii] reducing the vulnerability of vulnerable classifiers (through data obfuscation) to preserve model and data privacy, and iii] exploring the privacy-performance tradeoff to study the usability of the data obfuscation techniques. An empirical study is conducted on three datasets and eight classifiers to explore the above objectives. The results of the initial research identify the vulnerability in classifiers and segregate the vulnerable and non-vulnerable classifiers. The additional experiments on data obfuscation techniques reveal their utility to render data and model privacy and also their capability to chalk out a privacy-performance tradeoff in most scenarios. The results can aid the practitioners with their choice of classifiers in different scenarios and contexts.

Matching raw audio signals with textual descriptions requires understanding the audio's content and the description's semantics and then drawing connections between the two modalities. This paper investigates a hybrid retrieval system that utilizes audio metadata as an additional clue to understand the content of audio signals before matching them with textual queries. We experimented with metadata often attached to audio recordings, such as keywords and natural-language descriptions, and we investigated late and mid-level fusion strategies to merge audio and metadata. Our hybrid approach with keyword metadata and late fusion improved the retrieval performance over a content-based baseline by 2.36 and 3.69 pp. mAP@10 on the ClothoV2 and AudioCaps benchmarks, respectively.

Online kernel selection is a fundamental problem of online kernel methods.In this paper,we study online kernel selection with memory constraint in which the memory of kernel selection and online prediction procedures is limited to a fixed budget. An essential question is what is the intrinsic relationship among online learnability, memory constraint, and data complexity? To answer the question,it is necessary to show the trade-offs between regret and memory constraint.Previous work gives a worst-case lower bound depending on the data size,and shows learning is impossible within a small memory constraint.In contrast, we present distinct results by offering data-dependent upper bounds that rely on two data complexities:kernel alignment and the cumulative losses of competitive hypothesis.We propose an algorithmic framework giving data-dependent upper bounds for two types of loss functions.For the hinge loss function,our algorithm achieves an expected upper bound depending on kernel alignment.For smooth loss functions,our algorithm achieves a high-probability upper bound depending on the cumulative losses of competitive hypothesis.We also prove a matching lower bound for smooth loss functions.Our results show that if the two data complexities are sub-linear,then learning is possible within a small memory constraint.Our algorithmic framework depends on a new buffer maintaining framework and a reduction from online kernel selection to prediction with expert advice. Finally,we empirically verify the prediction performance of our algorithms on benchmark datasets.