The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.

Machine Learning (ML) provides important techniques for classification and predictions. Most of these are black-box models for users and do not provide decision-makers with an explanation. For the sake of transparency or more validity of decisions, the need to develop explainable/interpretable ML-methods is gaining more and more importance. Certain questions need to be addressed: How does an ML procedure derive the class for a particular entity? Why does a particular clustering emerge from a particular unsupervised ML procedure? What can we do if the number of attributes is very large? What are the possible reasons for the mistakes for concrete cases and models? For binary attributes, Formal Concept Analysis (FCA) offers techniques in terms of intents of formal concepts, and thus provides plausible reasons for model prediction. However, from the interpretable machine learning viewpoint, we still need to provide decision-makers with the importance of individual attributes to the classification of a particular object, which may facilitate explanations by experts in various domains with high-cost errors like medicine or finance. We discuss how notions from cooperative game theory can be used to assess the contribution of individual attributes in classification and clustering processes in concept-based machine learning. To address the 3rd question, we present some ideas on how to reduce the number of attributes using similarities in large contexts.

We have seen an explosion in developer tools and platforms related to machine learning and artificial intelligence during the last few years. From cloud-based cognitive APIs to libraries to frameworks to pre-trained models, developers make many choices to infuse AI into their applications. AI engineers and researchers choose a framework to train machine learning models. These frameworks abstract the underlying hardware and software stack to expose a simple API in languages such as Python and R. For example, an ML developer can leverage the parallelism offered by GPUs to accelerate a training job without changing much of the code written for the CPU. These frameworks expose simpler APIs that translate to complex mathematical computations and numerical analysis often needed for training the machine learning models. Apart from training, the machine learning frameworks simplify inference -- the process of utilizing a trained model for performing prediction or classification of live data.

In our day-to-day life we come across many problems in which we have certain problems that revolves around choosing a category such as pass/fail, win/lose, alive/dead,healthy/sick,Yes/No, etc. Decision making plays an important role in our life and selecting any of the choice has its own consequences. By reading the above stuff's, you may dwell with the question whether to proceed with this blog or skip it? Come on lets dive in assuming that you have chosen the YES Category. It was a good choice. It was an easy task for you but what if I have asked you that whether a random person with your age is likely to read my blog or not?

This is a starter tutorial on modeling using Keras which includes hyper-parameter tuning along with callbacks. Creating a Keras-Regression model that can accurately analyse features of a given house and predict the price accordingly. We would be using numpy and pandas for processing our dataset, matplotlib and seaborn for data visualization, and Keras for implementing our neural network. Also, we would be using Sklearn for outlier detection and scaling our dataset. We would first see all the features having missing values. This would include data from both training and testing data.

Data Science is one of the most sought fields in this century. Ever wonder why data is so important? Why researchers, scientists and business managers around the world are glued to their screens analyzing and manipulating data, finding better and efficient ways to use it? We humans always try to make our lives efficient and easy. But throughout the history of mankind, life has never been easy (that's a different issue).

Efficient simulation of SDEs is essential in many applications, particularly for ergodic systems that demand efficient simulation of both short-time dynamics and large-time statistics. However, locally Lipschitz SDEs often require special treatments such as implicit schemes with small time-steps to accurately simulate the ergodic measure. We introduce a framework to construct inference-based schemes adaptive to large time-steps (ISALT) from data, achieving a reduction in time by several orders of magnitudes. The key is the statistical learning of an approximation to the infinite-dimensional discrete-time flow map. We explore the use of numerical schemes (such as the Euler-Maruyama, a hybrid RK4, and an implicit scheme) to derive informed basis functions, leading to a parameter inference problem. We introduce a scalable algorithm to estimate the parameters by least squares, and we prove the convergence of the estimators as data size increases. We test the ISALT on three non-globally Lipschitz SDEs: the 1D double-well potential, a 2D multi-scale gradient system, and the 3D stochastic Lorenz equation with degenerate noise. Numerical results show that ISALT can tolerate time-step magnitudes larger than plain numerical schemes. It reaches optimal accuracy in reproducing the invariant measure when the time-step is medium-large.

Nonconvex optimization has been widely adopted in various domains, including image recognition (Hinton et al., 2012; Krizhevsky et al., 2012), Bayesian graphical models (Jordan et al., 2004; Attias, 2000), recommendation systems (Salakhutdinov et al., 2007), etc. Despite the fact that solving a nonconvex problem is generally difficult, empirical evidences have shown that simple first order algorithms such as stochastic gradient descent (SGD), are able to solve a majority of the aforementioned nonconvex problems efficiently. The theory behind these empirical observations, however, is still largely unexplored. In classical optimization literature, there have been fruitful results on characterizing the convergence of SGD to first-order stationary points for nonconvex problems. However, these types of results fall short of explaining the empirical evidences that SGD often converges to global minima for a wide class of nonconvex problems used in practice. More recently, understanding the role of noise in the algorithmic behavior of SGD has received significant attention. For instance, Jin et al. (2017) show that a perturbed form of gradient descent is able to escape from strict saddle points and converge to second-order stationary points (i.e., local minima). Zhou et al. (2019) further show that noise in the update can help SGD to escape from spurious local minima and converge to the global minima.

In this paper, we study communication efficient distributed algorithms for distributionally robust federated learning via periodic averaging with adaptive sampling. In contrast to standard empirical risk minimization, due to the minimax structure of the underlying optimization problem, a key difficulty arises from the fact that the global parameter that controls the mixture of local losses can only be updated infrequently on the global stage. To compensate for this, we propose a Distributionally Robust Federated Averaging (DRFA) algorithm that employs a novel snapshotting scheme to approximate the accumulation of history gradients of the mixing parameter. We analyze the convergence rate of DRFA in both convex-linear and nonconvex-linear settings. We also generalize the proposed idea to objectives with regularization on the mixture parameter and propose a proximal variant, dubbed as DRFA-Prox, with provable convergence rates. We also analyze an alternative optimization method for regularized cases in strongly-convex-strongly-concave and non-convex (under PL condition)-strongly-concave settings. To the best of our knowledge, this paper is the first to solve distributionally robust federated learning with reduced communication, and to analyze the efficiency of local descent methods on distributed minimax problems. We give corroborating experimental evidence for our theoretical results in federated learning settings.

Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate-models. In this context, the Linear-Inverse-Modeling (LIM) approach, by capturing a few essential interactions between dynamical components of the full system, has proven valuable in providing insights into predictability of the full system. We demonstrate that Reservoir Computing (RC), a form of learning suitable for systems with chaotic dynamics, provides an alternative nonlinear approach that improves on the predictive skill of the LIM approach. We do this in the example setting of predicting sea-surface-temperature in the North Atlantic in the pre-industrial control simulation of a popular earth system model, the Community-Earth-System-Model so that we can compare the performance of the new RC based approach with the traditional LIM approach both when learning data is plentiful and when such data is more limited. The improved predictive skill of the RC approach over a wide range of conditions -- larger number of retained EOF coefficients, extending well into the limited data regime, etc. -- suggests that this machine-learning technique may have a use in climate predictability studies. While the possibility of developing a climate emulator -- the ability to continue the evolution of the system on the attractor long after failing to be able to track the reference trajectory -- is demonstrated in the Lorenz-63 system, it is suggested that further development of the RC approach may permit such uses of the new approach in more realistic predictability studies.