Given a set of data points $\{x {(1)}, ..., x {(m)}\}$ associated to a set of outcomes $\{y {(1)}, ..., y {(m)}\}$, we want to build a classifier that learns how to predict $y$ from $x$. Hypothesis ― The hypothesis is noted $h_\theta$ and is the model that we choose. For a given input data $x {(i)}$ the model prediction output is $h_\theta(x {(i)})$. Loss function ― A loss function is a function $L:(z,y)\in\mathbb{R}\times Y\longmapsto L(z,y)\in\mathbb{R}$ that takes as inputs the predicted value $z$ corresponding to the real data value $y$ and outputs how different they are. Remark: Stochastic gradient descent (SGD) is updating the parameter based on each training example, and batch gradient descent is on a batch of training examples.

Like many problems in AI in their general form, supervised learning is computationally intractable. We hypothesize that an important reason humans can learn highly complex and varied concepts, in spite of the computational difficulty, is that they benefit tremendously from experienced and insightful teachers. This paper proposes a new learning framework that provides a role for a knowledgeable, benevolent teacher to guide the process of learning a target concept in a series of "curricular" phases or rounds. In each round, the teacher's role is to act as a moderator, exposing the learner to a subset of the available training data to move it closer to mastering the target concept. Via both theoretical and empirical evidence, we argue that this framework enables simple, efficient learners to acquire very complex concepts from examples. In particular, we provide multiple examples of concept classes that are known to be unlearnable in the standard PAC setting along with provably efficient algorithms for learning them in our extended setting. A key focus of our work is the ability to learn complex concepts on top of simpler, previously learned, concepts---a direction with the potential of creating more competent artificial agents.

A data set is called imbalanced if it contains many more samples from one class than from the rest of the classes. Data sets are unbalanced when at least one class is represented by only a small number of training examples (called the minority class) while other classes make up the majority. In this scenario, classifiers can have good accuracy on the majority class but very poor accuracy on the minority class(es) due to the influence that the larger majority class. The common example of such dataset is credit card fraud detection, where data points for fraud 1, are usually very less in comparison to fraud 0. There are many reasons why a dataset might be imbalanced: the category one is targeting might be very rare in the population, or the data might simply be difficult to collect. Let's solve the problem of an imbalanced dataset by working on one such dataset.

PageRank for Semi-Supervised Learning has shown to leverage data structures and limited tagged examples to yield meaningful classification. Despite successes, classification performance can still be improved, particularly in cases of fuzzy graphs or unbalanced labeled data. To address such limitations, a novel approach based on powers of the Laplacian matrix $L^\gamma$ ($\gamma > 0$), referred to as $L^\gamma$-PageRank, is proposed. Its theoretical study shows that it operates on signed graphs, where nodes belonging to one same class are more likely to share positive edges while nodes from different classes are more likely to be connected with negative edges. It is shown that by selecting an optimal $\gamma$, classification performance can be significantly enhanced. A procedure for the automated estimation of the optimal $\gamma$, from a unique observation of data, is devised and assessed. Experiments on several datasets demonstrate the effectiveness of both $L^\gamma$-PageRank classification and the optimal $\gamma$ estimation.

Machine learning systems, if not constrained, will compounding existing challenges to fairness in society often learn the simplest associations that can predict the labels, so at large. In this paper, we introduce a suite of threshold-agnostic any incorrect associations present in the training data can produce metrics that provide a nuanced view of this unintended bias, by unintended associations in the final model. Toxicity models specifically considering the various ways that a classifier's score distribution have been shown to capture and reproduce biases common can vary across designated groups. We also introduce a large new in society, for example mis-associating the names of frequently test set of online comments with crowd-sourced annotations for attacked identity groups (such as "gay", and "muslim" etc.) with identity references. We use this to show how our metrics can be toxicity [5, 17]. This unintended model bias could be due to the used to find new and potentially subtle unintended bias in existing demographic composition of the online user pool, the latent or public models.

On Valentine's Day, a non-profit research company called OpenAI, gifted us a paper with a blog post that rocked my world as an educator. We've trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization -- all without task-specific training. In other words, they had demonstrated how a language processing AI could learn, from millions of webpages, how to undertake written tasks (some of which are of reasonably high quality in terms of sense and coherence) without specifically being trained to do this via a supervised learning process. To understand the implications of the research, it is worth trying to get to grips with what supervised and unsupervised machine learning is (for someone like me this is a steep learning curve!). In supervised learning problems, we start with a data set containing training examples with associated correct labels.

Since the introduction and the public availability of the \textsc{ucr} time series benchmark data sets, numerous Time Series Classification (TSC) methods has been designed, evaluated and compared to each others. We suggest a critical view of TSC performance evaluation protocols put in place in recent TSC literature. The main goal of this `position' paper is to stimulate discussion and reflexion about performance evaluation in TSC literature.

Distant supervision for relation extraction heavily suffers from the wrong labeling problem. To alleviate this issue in news data with the timestamp, we take a new factor time into consideration and propose a novel time-aware distant supervision framework (Time-DS). Time-DS is composed of a time series instance-popularity and two strategies. Instance-popularity is to encode the strong relevance of time and true relation mention. Therefore, instance-popularity would be an effective clue to reduce the noises generated through distant supervision labeling. The two strategies, i.e., hard filter and curriculum learning are both ways to implement instance-popularity for better relation extraction in the manner of Time-DS. The curriculum learning is a more sophisticated and flexible way to exploit instance-popularity to eliminate the bad effects of noises, thus get better relation extraction performance. Experiments on our collected multi-source news corpus show that Time-DS achieves significant improvements for relation extraction.

Ahead of the 2019 TensorFlow Dev Summit, Google is announcing a new way for third-party developers to adopt differential privacy when training machine learning models. TensorFlow Privacy is designed to be easy to implement for developers already using the popular open-source ML library. The goal (via The Verge) of differential privacy for machine learning is to only "encode general patterns rather than facts about specific training examples." This allows user data to remain private, while the system overall still learns and can advance from general behavior. In particular, when training on users' data, those techniques offer strong mathematical guarantees that models do not learn or remember the details about any specific user.

Today, we're excited to announce TensorFlow Privacy (GitHub), an open source library that makes it easier not only for developers to train machine-learning models with privacy, but also for researchers to advance the state of the art in machine learning with strong privacy guarantees. Modern machine learning is increasingly applied to create amazing new technologies and user experiences, many of which involve training machines to learn responsibly from sensitive data, such as personal photos or email. Ideally, the parameters of trained machine-learning models should encode general patterns rather than facts about specific training examples. To ensure this, and to give strong privacy guarantees when the training data is sensitive, it is possible to use techniques based on the theory of differential privacy. In particular, when training on users' data, those techniques offer strong mathematical guarantees that models do not learn or remember the details about any specific user.