Stroke is the second leading cause of death worldwide. According to the World Health Organization [1], 5 million people worldwide suffer a stroke every year. Of these, one third die and another third are left permanently disabled. In the United States, someone has a stroke every 40 seconds and every four minutes, someone dies [2]. The aftermath is devastating, with victims experiencing a wide range of disabling symptoms including sudden paralysis, speech loss or blindness due to blood flow interruption in the brain [3].

Many different fish species travel vast distances every year to reach their breeding grounds. Nowadays this journey is made more difficult due to obstacles such as water locks. One of these water locks placed along a popular route for migrating fish is the Weerdsluis in Utrecht. In order raise awareness, an initiative was launched together with the municipality of Utrecht: the Fish Doorbell. Here users could watch a livestream of the waters at the lock, and'ring' a bell if they spotted a fish.

'Machine Learning is all about how a machine with an artificial intelligence learns like a human being' Welcome to the course on Machine Learning and Implementing it using Python 3. As the title says, this course recommends to have a basic knowledge in Python 3 to grasp the implementation part easily but it is not compulsory. This course has strong content on the core concepts of ML such as it's features, the steps involved in building a ML Model – Data Preprocessing, Finetuning the Model, Overfitting, Underfitting, Bias, Variance, Confusion Matrix and performance measures of a ML Model. We'll understand the importance of many preprocessing techniques such as Binarization, MinMaxScaler, Standard Scaler We can implement many ML Algorithms in Python using scikit-learn library in a few lines. Can't we? Yet, that won't help us to understand the algorithms. Hence, in this course, we'll first look into understanding the mathematics and concepts behind the algorithms and then, we'll implement the same in Python.

'Machine Learning is all about how a machine with an artificial intelligence learns like a human being' Welcome to the course on Machine Learning and Implementing it using Python 3. As the title says, this course recommends to have a basic knowledge in Python 3 to grasp the implementation part easily but it is not compulsory. This course has strong content on the core concepts of ML such as it's features, the steps involved in building a ML Model - Data Preprocessing, Finetuning the Model, Overfitting, Underfitting, Bias, Variance, Confusion Matrix and performance measures of a ML Model. We'll understand the importance of many preprocessing techniques such as Binarization, MinMaxScaler, Standard Scaler We can implement many ML Algorithms in Python using scikit-learn library in a few lines. Can't we? Yet, that won't help us to understand the algorithms. Hence, in this course, we'll first look into understanding the mathematics and concepts behind the algorithms and then, we'll implement the same in Python.

Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-world applications, accuracy is only one of the multiple -- often conflicting -- performance criteria, necessitating the adoption of a multi-objective (MO) perspective. While the literature on MO optimization is rich, few prior studies have focused on HPO. In this paper, we propose algorithms that extend asynchronous successive halving (ASHA) to the MO setting. Considering multiple evaluation metrics, we assess the performance of these methods on three real world tasks: (i) Neural architecture search, (ii) algorithmic fairness and (iii) language model optimization. Our empirical analysis shows that MO ASHA enables to perform MO HPO at scale. Further, we observe that that taking the entire Pareto front into account for candidate selection consistently outperforms multi-fidelity HPO based on MO scalarization in terms of wall-clock time. Our algorithms (to be open-sourced) establish new baselines for future research in the area.

The diagnosis of blood-based diseases often involves identifying and characterizing patient blood samples. Automated methods to detect and classify blood cell subtypes have important medical applications. Automated medical image processing and analysis offers a powerful tool for medical diagnosis. In this work we tackle the problem of white blood cell classification based on the morphological characteristics of their outer contour, color. The work we would explore a set of preprocessing and segmentation (Color-based segmentation, Morphological processing, contouring) algorithms along with a set of features extraction methods (Corner detection algorithms and Histogram of Gradients (HOG)), dimentionality reduction algorithms (Principal Component Analysis (PCA)) that are able to recognize and classify through various Unsupervised (k-nearest neighbors) and Supervised (Support Vector Machine, Decision Trees, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Naïve Bayes) algorithms different categories of white blood cells to Eosinophil, Lymphocyte, Monocyte, and Neutrophil. We even take a step forwards to explore various Deep Convolutional Neural network architecture (Sqeezent, MobilenetV1, MobilenetV2, InceptionNet etc.) without preprocessing/segmentation and with preprocessing. We would like to explore many algorithms to identify the robust algorithm with least time complexity and low resource requirement. The outcome of this work can be a cue to selection of algorithms as per requirement for automated blood cell classification.

We introduce ParK, a new large-scale solver for kernel ridge regression. Our approach combines partitioning with random projections and iterative optimization to reduce space and time complexity while provably maintaining the same statistical accuracy. In particular, constructing suitable partitions directly in the feature space rather than in the input space, we promote orthogonality between the local estimators, thus ensuring that key quantities such as local effective dimension and bias remain under control. We characterize the statistical-computational tradeoff of our model, and demonstrate the effectiveness of our method by numerical experiments on large-scale datasets.

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss, to extract slowly varying latent representations. Rather than producing individual predictions for each of the future representations, the model emits a sequence of predictions shorter than the sequence of upcoming representations to which they will be aligned. In this way, the prediction network solves a simpler task of predicting the next symbols, but not their exact timing, while the encoding network is trained to produce piece-wise constant latent codes. We evaluate the model on a speech coding task and demonstrate that the proposed Aligned Contrastive Predictive Figure 1: ACPC architecture. The encoder maps chunks of input Coding (ACPC) leads to higher linear phone prediction accuracy data into a latent space and the autoregressive model predicts and lower ABX error rates, while being slightly faster to K upcoming latent vectors. They are aligned using DTW to the train due to the reduced number of prediction heads.

Hate speech detection has become a hot topic in recent years due to the exponential growth of offensive language in social media. It has proven that, state-of-the-art hate speech classifiers are efficient only when tested on the data with the same feature distribution as training data. As a consequence, model architecture plays the second role to improve the current results. In such a diverse data distribution relying on low level features is the main cause of deficiency due to natural bias in data. That's why we need to use high level features to avoid a biased judgement. In this paper, we statistically analyze the Perspective Scores and their impact on hate speech detection. We show that, different hate speech datasets are very similar when it comes to extract their Perspective Scores. Eventually, we prove that, over-sampling the Perspective Scores of a hate speech dataset can significantly improve the generalization performance when it comes to be tested on other hate speech datasets.

Learning with noisy labels is a practically challenging problem in weakly supervised learning. In the existing literature, open-set noises are always considered to be poisonous for generalization, similar to closed-set noises. In this paper, we empirically show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. Inspired by the observations, we propose a simple yet effective regularization by introducing Open-set samples with Dynamic Noisy Labels (ODNL) into training. With ODNL, the extra capacity of the neural network can be largely consumed in a way that does not interfere with learning patterns from clean data. Through the lens of SGD noise, we show that the noises induced by our method are random-direction, conflict-free and biased, which may help the model converge to a flat minimum with superior stability and enforce the model to produce conservative predictions on Out-of-Distribution instances. Extensive experimental results on benchmark datasets with various types of noisy labels demonstrate that the proposed method not only enhances the performance of many existing robust algorithms but also achieves significant improvement on Out-of-Distribution detection tasks even in the label noise setting.