Accurate estimation of the positions and shapes of microscale objects is crucial for automated imaging-guided manipulation using a non-contact technique such as optical tweezers. Perception methods that use traditional computer vision algorithms tend to fail when the manipulation environments are crowded. In this paper, we present a deep learning model for semantic segmentation of the images representing such environments. Our model successfully performs segmentation with a high mean Intersection Over Union score of 0.91.

Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to $1 - 10^{-9}$ for realistic use cases; this important requirement, however, is often overlooked in literature. In recent years, descriptors based on deep convolutional neural networks have matched or surpassed traditional feature extraction methods in content-based image retrieval tasks. To the best of our knowledge, ours is the first attempt to establish the performance range of deep learning-based descriptors for unsupervised near-duplicate detection on a range of datasets, encompassing a broad spectrum of near-duplicate definitions. We leverage both established and new benchmarks, such as the Mir-Flick Near-Duplicate (MFND) dataset, in which a known ground truth is provided for all possible pairs over a general, large scale image collection. To compare the specificity of different descriptors, we reduce the problem of unsupervised detection to that of binary classification of near-duplicate vs. not-near-duplicate images. The latter can be conveniently characterized using Receiver Operating Curve (ROC). Our findings in general favor the choice of fine-tuning deep convolutional networks, as opposed to using off-the-shelf features, but differences at high specificity settings depend on the dataset and are often small. The best performance was observed on the MFND benchmark, achieving 96\% sensitivity at a false positive rate of $1.43 \times 10^{-6}$.

Epilepsy is a neurological disorder classified as the second most serious neurological disease known to humanity, after stroke. Localization of epileptogenic zone is an important step for epileptic patient treatment, which starts with epileptic spike detection. The common practice for spike detection of brain signals is via visual scanning of the recordings, which is a subjective and a very time-consuming task. Motivated by that, this paper focuses on using machine learning for automatic detection of epileptic spikes in magnetoencephalography (MEG) signals. First, we used the Position Weight Matrix (PWM) method combined with a uniform quantizer to generate useful features. Second, the extracted features are classified using a Support Vector Machine (SVM) for the purpose of epileptic spikes detection. The proposed technique shows great potential in improving the spike detection accuracy and reducing the feature vector size. Specifically, the proposed technique achieved average accuracy up to 98% in using 5-folds cross-validation applied to a balanced dataset of 3104 samples. These samples are extracted from 16 subjects where eight are healthy and eight are epileptic subjects using a sliding frame of size of 100 samples-points with a step-size of 2 sample-points.

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and result in more interpretable explanations. We introduce two novel metrics to quantitatively evaluate local interpretability at the instance level. We use these metrics to illustrate the effectiveness of our method on an image and tabular dataset, respectively MNIST and Breast Cancer Wisconsin (Diagnostic). The method also eliminates the computational bottleneck that arises because of numerical gradient evaluation for $\textit{black box}$ models.

Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons. We present a novel approach which, in addition to the scarce labeled data (training pairs), allows to train fMRI-to-image reconstruction networks also on "unlabeled" data (i.e., images without fMRI recording, and fMRI recording without images). The proposed model utilizes both an Encoder network (image-to-fMRI) and a Decoder network (fMRI-to-image). Concatenating these two networks back-to-back (Encoder-Decoder & Decoder-Encoder) allows augmenting the training with both types of unlabeled data. Importantly, it allows training on the unlabeled test-fMRI data. This self-supervision adapts the reconstruction network to the new input test-data, despite its deviation from the statistics of the scarce training data.

Federated learning enables a large amount of edge computing devices to learn a centralized model while keeping all local data on edge devices. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once in a while. Despite its simplicity, it lacks theoretical guarantees in the federated setting. In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data. We investigate the effect of different sampling and averaging schemes, which are crucial especially when data are unbalanced. We prove a concise convergence rate of $\mathcal{O}(\frac{1}{T})$ for \texttt{FedAvg} with proper sampling and averaging schemes in convex problems, where $T$ is the total number of steps. Our results show that heterogeneity of data slows down the convergence, which is intrinsic in the federated setting. Low device participation rate can be achieved without severely harming the optimization process in federated learning. We show that there is a trade-off between communication efficiency and convergence rate. We analyze the necessity of learning rate decay by taking a linear regression as an example. Our work serves as a guideline for algorithm design in applications of federated learning, where heterogeneity and unbalance of data are the common case.

We theoretically prove that the generalization performance of deep neural networks (DNNs) is mainly determined by an intrinsic low-dimensional structure of data. Recently, DNNs empirically provide outstanding performance in various machine learning applications. Motivated by the success, theoretical properties of DNNs (e.g. a generalization error) are actively investigated by numerous studies toward understanding their mechanism. Especially, how DNNs behave with high-dimensional data is one of the most important concerns. However, the problem is not sufficiently investigated from an aspect of characteristics of data, despite it is frequently observed that high-dimensional data have an intrinsic low-dimensionality in practice. In this paper, to clarify a connection between DNNs and such the data, we derive bounds for approximation and generalization errors by DNNs with intrinsic low-dimensional data. To the end, we introduce a general notion of an intrinsic dimension and develop a novel proof technique to evaluate the errors. Consequently, we show that convergence rates of the errors by DNNs do not depend on the nominal high-dimensionality of data, but depend on the lower intrinsic dimension. We also show that the rate is optimal in the minimax sense. Furthermore, we find that DNNs with increasing layers can handle a broader class of intrinsic low-dimensional data. We conduct a numerical simulation to validate (i) the intrinsic dimension of data affects the generalization error of DNNs, and (ii) DNNs outperform other non-parametric estimators which are also adaptive to the intrinsic dimension.

Continuous symmetries and their breaking play a prominent role in contemporary physics. Effective low-energy field theories around symmetry breaking states explain diverse phenomena such as superconductivity, magnetism, and the mass of nucleons. We show that such field theories can also be a useful tool in machine learning, in particular for loss functions with continuous symmetries that are spontaneously broken by random initializations. In this paper, we illuminate our earlier published work (Bamler & Mandt, 2018) on this topic more from the perspective of theoretical physics. We show that the analogies between superconductivity and symmetry breaking in temporal representation learning are rather deep, allowing us to formulate a gauge theory of `charged' embedding vectors in time series models. We show that making the loss function gauge invariant speeds up convergence in such models.

In neuroimaging, multiple automated methods have been developed for various problems, such as brain extraction, segmentation of anatomical regions of interest (ROIs), white matter lesion (WML) segmentation and segmentation of brain tumor sub-regions. Importantly, each of these problems have their own specific challenges, mainly due to variations in image modalities and imaging signatures that best characterize target regions. These variations motivated development of a large number of distinct task-specific segmentation methods (Kalavathi P, 2016; Anbeek et al., 2004; Eugenio Iglesias and Sabuncu, 2014; Gordillo et al., 2013; Despotovic et al., 2015). Machine learning has played a key role in enabling novel methods that achieved accuracy comparable to, or surpassing human raters. In the commonly used supervised learning framework, examples with ground-truth labels are presented to the learning algorithm in order to construct a model that learns imaging patterns that characterize the target segmentations.

This paper describes the main algorithms implemented and documents the API of libconform. Also some details about the implementation and changes in future versions are described.