University of Toronto graduate student Avishek "Joey" Bose, under the supervision of associate professor Parham Aarabi in the school's department of electrical and computer engineering, has created an algorithm that dynamically disrupts facial recognition systems. The project has privacy-related and even safety-related implications for systems that use so-called machine learning -- and for all of us whose data may be used in ways we don't realize. Major companies such as Amazon, Google, Facebook and Netflix are today leveraging machine learning. Financial trading firms and health care companies are using it, too -- as are smart car manufacturers. What is machine learning, anyway?

For many AI services, it is critical to be able to comprehend human language and even converse in it with human users. So far, advances in natural language processing (NLP) powered with "sub-symbolic" machine learning based on deep neural networks allows us to solve multiple tasks like machine translation, classification, and emotion recognition. However, using these approaches requires enormous amount of training. Additionally, there are increasing legal restrictions in particular applications due to recent regulations, making current solutions unviable. The ultimate goal for these industry initiatives is to allow humans and AI to interact fluently in a common language.

LAHORE - An exhibition titled "2nd Machine Learning Projects" featuring projects of International Technology University students on Artificial Intelligence opened at the Punjab Signal Processing and Information Decoding Research Laboratory on Sunday. The exhibition opened after four-month training of MS and PhD students of ITU who presented their Machine Learning course projects, geared towards solving interesting and locally relevant problems. The projects included a project on grocery stores who always find difficult to forecast sales and purchase of items. The project Walmart Data is aimed at predicting unit sales quantities of sales items across 54 grocery stores using the technique of rolling means and LSTM neural. This project will help managers in warehouse management, manpower estimation and effective sales promotions.

Anthony Seldon is one of Britain's leading educationalists and social commentators. He has served as a close adviser to former leaders, including Tony Blair and David Cameron. In recent years, he has turned his attention to the ongoing impact of new technologies, in particular, artificial intelligence (AI), on education and on society, writes Kyran Fitzgerald. With Oladimeji Abidoye, Mr Seldon recently published The Fourth Education Revolution: Will Artificial intelligence Liberate or Infantilise Humanity? He does not pull his punches, warning that we may be "sleepwalking into the biggest potential disaster of modern times". Despite these tides of change, the education sector has been slow to respond.

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing. We use a generator network to propose tasks for the agent to try to achieve, specified as goal states. The generator network is optimized using adversarial training to produce tasks that are always at the appropriate level of difficulty for the agent. Our method thus automatically produces a curriculum of tasks for the agent to learn. We show that, by using this framework, an agent can efficiently and automatically learn to perform a wide set of tasks without requiring any prior knowledge of its environment. Our method can also learn to achieve tasks with sparse rewards, which traditionally pose significant challenges.

A reciprocal recommendation problem is one where the goal of learning is not just to predict a user's preference towards a passive item (e.g., a book), but to recommend the targeted user on one side another user from the other side such that a mutual interest between the two exists. The problem thus is sharply different from the more traditional items-to-users recommendation, since a good match requires meeting the preferences of both users. We initiate a rigorous theoretical investigation of the reciprocal recommendation task in a specific framework of sequential learning. We point out general limitations, formulate reasonable assumptions enabling effective learning and, under these assumptions, we design and analyze a computationally efficient algorithm that uncovers mutual likes at a pace comparable to those achieved by a clearvoyant algorithm knowing all user preferences in advance. Finally, we validate our algorithm against synthetic and real-world datasets, showing improved empirical performance over simple baselines.

We consider a network scenario in which agents can evaluate each other according to a score graph that models some interactions. The goal is to design a distributed protocol, run by the agents, that allows them to learn their unknown state among a finite set of possible values. We propose a Bayesian framework in which scores and states are associated to probabilistic events with unknown parameters and hyperparameters, respectively. We show that each agent can learn its state by means of a local Bayesian classifier and a (centralized) Maximum-Likelihood (ML) estimator of parameter-hyperparameter that combines plain ML and Empirical Bayes approaches. By using tools from graphical models, which allow us to gain insight on conditional dependencies of scores and states, we provide a relaxed probabilistic model that ultimately leads to a parameter-hyperparameter estimator amenable to distributed computation. To highlight the appropriateness of the proposed relaxation, we demonstrate the distributed estimators on a social interaction setup for user profiling. A common feature of online social networks (OSNs) is the possibility of individuals to continuously interact among themselves, by sharing contents and expressing opinions or ratings on different topics [1], [2].

For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirty" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same entity. In databases, this issue is typically solved with a deduplication step. We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains. We study a generalization of one-hot encoding, similarity encoding, that builds feature vectors from similarities across categories. We perform a thorough empirical validation on non-curated tables, a problem seldom studied in machine learning. Results on seven real-world datasets show that similarity encoding brings significant gains in prediction in comparison with known encoding methods for categories or strings, notably one-hot encoding and bag of character n-grams. We draw practical recommendations for encoding dirty categories: 3-gram similarity appears to be a good choice to capture morphological resemblance. For very high-cardinality, dimensionality reduction significantly reduces the computational cost with little loss in performance: random projections or choosing a subset of prototype categories still outperforms classic encoding approaches.

This course gives an overview of modern data-driven techniques for natural language processing. The course moves from shallow bag-of-words models to richer structural representations of how words interact to create meaning. At each level, we will discuss the salient linguistic phemonena and most successful computational models. Along the way we will cover machine learning techniques which are especially relevant to natural language processing. Readings will be drawn mainly from my notes.

Editor's note: A version of this commentary by Brigham Young University professor Darin Gates was published by BYU's Wheatley Institution on May 22. Artificial intelligence, or AI, generates the most pressing ethical questions of any technology today, in part because of the nearly ubiquitous influence it will have in so many areas of our lives. AI will have an immense ethical impact both in terms of the amount of good it can bring about, and in terms of the potential harms it can unleash. Interest in the ethical dimensions of AI has increased dramatically in recent years -- from the nearly daily reporting of ethical-related AI issues in various news outlets, to major companies such as Amazon, Google, Facebook, DeepMind, Microsoft and IBM coming together to create the Partnership on AI to Benefit People and Society. Elon Musk, the late Stephen Hawking and 8,000 others have signed an open letter with concerns about the future of AI. There has thus been an increasing recognition for the need to focus on the ethical aspects of AI. Here are some of the most significant ethical issues facing the continued implementation of artificial intelligence.