CEO at Things Foundation, Technology Manager at Let's Do It Foundation Head of Cortex Ventures- Africa's first AI only focused VC Fund

HYDERABAD: A mere 1137 candidates out of 3,82,116 failed candidates been declared passed in the intermediate re-verification results, which are released on Monday. The Telangana State Board of Intermediate Education (TSBIE) officials announced that results of 552 candidates from the second year and 585 candidates from the first year have been changed from failed to pass after the board carried out thorough re-verification of their answer scripts. Although the results have been released, candidates will be able to download the revised marks as well as the scanned copy of the answer script from Tuesday evening along with the subject wise result. As per the directions of the High court, the board had taken up the re-verification of the failed candidates answer scripts on April 26, 2019. They had set up 12 spot valuation camps to verify a total of 9, 02, 429 answer scripts. The board said that they have used services of 5,831 qualified lecturers as Chief Examiners and Assistant examiners and completed the re-verification of 9.02 lakh answer scripts by May 5, 2019.

What will happen when an AI will be entirely blamed for its actions? It brings up important points that we will all have to contend with soon! We'll have truly entered the age of AI when we can throw that AI in jail for bad behavior. My books on Amazon: The Little Book of Fundamental Indicators: Hands-On Market Analysis with Python: Find Your Market Bearings with Python, Jupyter Notebooks, and Freely Available Data: https://amzn.to/2DERG3d Create Income Streams with Online Classes: Design Classes That Generate Long-Term Revenue: https://amzn.to/2VToEHK The story itself is entertaining, and let me give you the 30 seconds low-down of what happened.

We explore the behavior of a standard convolutional neural net in a setting that introduces classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned tasks. This setting corresponds to that which human learners face as they acquire domain expertise, for example, as an individual reads a textbook chapter-by-chapter. Through simulations involving sequences of ten related tasks, we find reason for optimism that nets will scale well as they advance from having a single skill to becoming domain experts. We observed two key phenomena. First, _forward facilitation_---the accelerated learning of task $n+1$ having learned $n$ previous tasks---grows with $n$. Second, _backward interference_---the forgetting of the $n$ previous tasks when learning task $n+1$---diminishes with $n$. Amplifying forward facilitation is the goal of research on metalearning, and attenuating backward interference is the goal of research on catastrophic forgetting. We find that both of these goals are attained simply through broader exposure to a domain.

The information-theoretic analysis by Russo and Van Roy (2014) in combination with minimax duality has proved a powerful tool for the analysis of online learning algorithms in full and partial information settings. In most applications there is a tantalising similarity to the classical analysis based on mirror descent. We make a formal connection, showing that the information-theoretic bounds in most applications can be derived from existing techniques for online convex optimisation. Besides this, for $k$-armed adversarial bandits we provide an efficient algorithm with regret that matches the best information-theoretic upper bound and improve best known regret guarantees for online linear optimisation on $\ell_p$-balls and bandits with graph feedback.

In this tutorial paper, we first define mean squared error, variance, covariance, and bias of both random variables and classification/predictor models. Then, we formulate the true and generalization errors of the model for both training and validation/test instances where we make use of the Stein's Unbiased Risk Estimator (SURE). We define overfitting, underfitting, and generalization using the obtained true and generalization errors. We introduce cross validation and two well-known examples which are $K$-fold and leave-one-out cross validations. We briefly introduce generalized cross validation and then move on to regularization where we use the SURE again. We work on both $\ell_2$ and $\ell_1$ norm regularizations. Then, we show that bootstrap aggregating (bagging) reduces the variance of estimation. Boosting, specifically AdaBoost, is introduced and it is explained as both an additive model and a maximum margin model, i.e., Support Vector Machine (SVM). The upper bound on the generalization error of boosting is also provided to show why boosting prevents from overfitting. As examples of regularization, the theory of ridge and lasso regressions, weight decay, noise injection to input/weights, and early stopping are explained. Random forest, dropout, histogram of oriented gradients, and single shot multi-box detector are explained as examples of bagging in machine learning and computer vision. Finally, boosting tree and SVM models are mentioned as examples of boosting.

Prior work has shown that the multi-relational embedding objective can be reformulated to learn dynamic knowledge graphs, enabling incremental class learning. The core contribution of our work is Incremental Semantic Initialization, which enables the multi-relational embedding parameters for a novel concept to be initialized in relation to previously learned embeddings of semantically similar concepts. We present three variants of our approach: Entity Similarity Initialization, Relational Similarity Initialization, and Hybrid Similarity Initialization, that reason about entities, relations between entities, or both, respectively. When evaluated on the mined AI2Thor dataset, our experiments show that incremental semantic initialization improves immediate query performance by 21.3 MRR* percentage points, on average. Additionally, the best performing proposed method reduced the number of epochs required to approach joint-learning performance by 57.4\% on average.

Machine learning is increasingly used in safety-critical applications, and hence designing machine learning algorithms in the presence of an adversary has been a topic of active research [2, 3, 4, 5, 11, 12, 13]. A style of adversary that is commonly studied is data poisoning attacks [4, 12, 15, 21] where the adversary can modify or corrupt a small fraction of training examples with the goal of forcing the trained classifier to have low classification accuracy. Such attacks have threatened many real-world applications including spam filters [23], malware detection [25], sentiment analysis [24] and collaborative filtering [15]. There has been a body of prior work on data poisoning with increasingly sophisticated attacks and defenses [4, 12, 15, 21, 22, 27, 29, 30]. However, the literature largely suffers from two main limitations. First, most work is on the batch setting - all data is provided in advance and the adversary assumes that the learner's goal is to produce an empirical minimizer of a loss. This excludes many modern machine learning algorithms, such as, stochastic gradient descent, or learning from a data stream.

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated learning problems simulated from two popular image classification datasets.

When pre-processing observational data via matching, we seek to approximate each unit with maximally similar peers that had an alternative treatment status--essentially replicating a randomized block design. However, as one considers a growing number of continuous features, a curse of dimensionality applies making asymptotically valid inference impossible (Abadie and Imbens, 2006). The alternative of ignoring plausibly relevant features is certainly no better, and the resulting trade-off substantially limits the application of matching methods to "wide" datasets. Instead, Li and Fu (2017) recasts the problem of matching in a metric learning framework that maps features to a low-dimensional space that facilitates "closer matches" while still capturing important aspects of unit-level heterogeneity. However, that method lacks key theoretical guarantees and can produce inconsistent estimates in cases of heterogeneous treatment effects. Motivated by straightforward extension of existing results in the matching literature, we present alternative techniques that learn latent matching features through either MLPs or through siamese neural networks trained on a carefully selected loss function. We benchmark the resulting alternative methods in simulations as well as against two experimental data sets--including the canonical NSW worker training program data set--and find superior performance of the neural-net-based methods.