A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success relies on the presence of domain labels, typically requiring manual annotation and careful curation of datasets. Here we focus on a less explored, but more realistic case: learning from data from multiple domains, without access to domain annotations. In this scenario, standard model training leads to the overfitting of large domains, while disregarding smaller ones. We address this limitation via dynamic residual adapters, an adaptive gating mechanism that helps account for latent domains, coupled with an augmentation strategy inspired by recent style transfer techniques. Our proposed approach is examined on image classification tasks containing multiple latent domains, and we showcase its ability to obtain robust performance across these. Dynamic residual adapters significantly outperform off-the-shelf networks with much larger capacity, and can be incorporated seamlessly with existing architectures in an end-to-end manner.

Learning accurate drug representation is essential for tasks such as computational drug repositioning and prediction of drug side-effects. A drug hierarchy is a valuable source that encodes human knowledge of drug relations in a tree-like structure where drugs that act on the same organs, treat the same disease, or bind to the same biological target are grouped together. However, its utility in learning drug representations has not yet been explored, and currently described drug representations cannot place novel molecules in a drug hierarchy. Here, we develop a semi-supervised drug embedding that incorporates two sources of information: (1) underlying chemical grammar that is inferred from molecular structures of drugs and drug-like molecules (unsupervised), and (2) hierarchical relations that are encoded in an expert-crafted hierarchy of approved drugs (supervised). We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the knowledge-based drug-drug similarity to induce the clustering of drugs in hyperbolic space. The hyperbolic space is amenable for encoding hierarchical concepts. Both quantitative and qualitative results support that the learned drug embedding can accurately reproduce the chemical structure and induce the hierarchical relations among drugs. Furthermore, our approach can infer the pharmacological properties of novel molecules by retrieving similar drugs from the embedding space. We demonstrate that the learned drug embedding can be used to find new uses for existing drugs and to discover side-effects. We show that it significantly outperforms baselines in both tasks.

We propose a model to tackle classification tasks in the presence of very little training data. To this aim, we approximate the notion of exact match with a theoretically sound mechanism that computes a probability of matching in the input space. Importantly, the model learns to focus on elements of the input that are relevant for the task at hand; by leveraging highlighted portions of the training data, an error boosting technique guides the learning process. In practice, it increases the error associated with relevant parts of the input by a given factor. Remarkable results on text classification tasks confirm the benefits of the proposed approach in both balanced and unbalanced cases, thus being of practical use when labeling new examples is expensive. In addition, by inspecting its weights, it is often possible to gather insights on what the model has learned.

The `signature method' refers to a collection of feature extraction techniques for multimodal sequential data, derived from the theory of controlled differential equations. Variations exist as many authors have proposed modifications to the method, so as to improve some aspect of it. Here, we introduce a \emph{generalised signature method} that contains these variations as special cases, and groups them conceptually into \emph{augmentations}, \emph{windows}, \emph{transforms}, and \emph{rescalings}. Within this framework we are then able to propose novel variations, and demonstrate how previously distinct options may be combined. We go on to perform an extensive empirical study on 26 datasets as to which aspects of this framework typically produce the best results. Combining the top choices produces a canonical pipeline for the generalised signature method, which demonstrates state-of-the-art accuracy on benchmark problems in multivariate time series classification.

A robustness certificate is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For {\it any} input perturbations with a magnitude smaller than the certificate value, the classification output will provably remain unchanged. Exactly computing the robustness certificates for neural networks is difficult since it requires solving a non-convex optimization. In this paper, we provide computationally-efficient robustness certificates for neural networks with differentiable activation functions in two steps. First, we show that if the eigenvalues of the Hessian of the network are bounded, we can compute a robustness certificate in the $l_2$ norm efficiently using convex optimization. Second, we derive a computationally-efficient differentiable upper bound on the curvature of a deep network. We also use the curvature bound as a regularization term during the training of the network to boost its certified robustness. Putting these results together leads to our proposed {\bf C}urvature-based {\bf R}obustness {\bf C}ertificate (CRC) and {\bf C}urvature-based {\bf R}obust {\bf T}raining (CRT). Our numerical results show that CRT leads to significantly higher certified robust accuracy compared to interval-bound propagation (IBP) based training. We achieve certified robust accuracy 69.79\%, 57.78\% and 53.19\% while IBP-based methods achieve 44.96\%, 44.74\% and 44.66\% on 2,3 and 4 layer networks respectively on the MNIST-dataset.

Embedding based models have been the state of the art in collaborative filtering for over a decade. Traditionally, the dot product or higher order equivalents have been used to combine two or more embeddings, e.g., most notably in matrix factorization. In recent years, it was suggested to replace the dot product with a learned similarity e.g. using a multilayer perceptron (MLP). This approach is often referred to as neural collaborative filtering (NCF). In this work, we revisit the experiments of the NCF paper that popularized learned similarities using MLPs. First, we show that with a proper hyperparameter selection, a simple dot product substantially outperforms the proposed learned similarities. Second, while a MLP can in theory approximate any function, we show that it is non-trivial to learn a dot product with an MLP. Finally, we discuss practical issues that arise when applying MLP based similarities and show that MLPs are too costly to use for item recommendation in production environments while dot products allow to apply very efficient retrieval algorithms. We conclude that MLPs should be used with care as embedding combiner and that dot products might be a better default choice.

Automated mitotic detection in time-lapse phasecontrast microscopy provides us much information for cell behavior analysis, and thus several mitosis detection methods have been proposed. However, these methods still have two problems; 1) they cannot detect multiple mitosis events when there are closely placed. 2) they do not consider the annotation gaps, which may occur since the appearances of mitosis cells are very similar before and after the annotated frame. In this paper, we propose a novel mitosis detection method that can detect multiple mitosis events in a candidate sequence and mitigate the human annotation gap via estimating a spatiotemporal likelihood map by 3DCNN. In this training, the loss gradually decreases with the gap size between ground truth and estimation. This mitigates the annotation gaps. Our method outperformed the compared methods in terms of F1- score using a challenging dataset that contains the data under four different conditions.

Recurrent neural networks (RNNs) are more suitable for learning non-linear dependencies in dynamical systems from observed time series data. In practice all the external variables driving such systems are not known a priori, especially in economical forecasting. A class of RNNs called Error Correction Neural Networks (ECNNs) was designed to compensate for missing input variables. It does this by feeding back in the current step the error made in the previous step. The ECNN is implemented in Python by the computation of the appropriate gradients and it is tested on stock market predictions. As expected it out performed the simple RNN and LSTM and other hybrid models which involve a de-noising pre-processing step. The intuition for the latter is that de-noising may lead to loss of information.

There are many types of python libraries available. Here I am mentioning some popular libraries for Machine Learning. NumPy is a general-purpose array-processing package. It provides a high-performance multidimensional array object and tools for working with these arrays. It is the fundamental package for scientific computing with Python.

Deep learning and machine learning both offer ways to train models and classify data. This video compares the two, and it offers ways to help you decide which one to use. Let's start by discussing the classic example of cats versus dogs. Now, in this picture, do you see a cat or a dog? How are you able to answer that? Chances are you've seen many cats and dogs over time, and so you've learned how to identify them.