Collaborating Authors

Continuing Education

This 5-star app makes learning a new language less boring


TL;DR: As of July 25, you can take half off a lifetime subscription to QLango Language Games -- dropping the price to just $44.99. Now, more than ever, people who want to learn a new language are turning to their mobile devices for help. But if you're looking for one that really shakes up the learning experience in an exciting way, check out QLango Language Games. QLango has earned 4.4 out of 5 stars on the Google Play store and for good reason. The interactive app is designed more like a game, rather than a structured learning environment.

Towards Knowledgeable Supervised Lifelong Learning Systems

Journal of Artificial Intelligence Research

Learning a sequence of tasks is a long-standing challenge in machine learning. This setting applies to learning systems that observe examples of a range of tasks at different points in time. A learning system should become more knowledgeable as more related tasks are learned. Although the problem of learning sequentially was acknowledged for the first time decades ago, the research in this area has been rather limited. Research in transfer learning, multitask learning, metalearning and deep learning has studied some challenges of these kinds of systems. Recent research in lifelong machine learning and continual learning has revived interest in this problem. We propose Proficiente, a full framework for long-term learning systems. Proficiente relies on knowledge transferred between hypotheses learned with Support Vector Machines. The first component of the framework is focused on transferring forward selectively from a set of existing hypotheses or functions representing knowledge acquired during previous tasks to a new target task. A second component of Proficiente is focused on transferring backward, a novel ability of long-term learning systems that aim to exploit knowledge derived from recent tasks to encourage refinement of existing knowledge. We propose a method that transfers selectively from a task learned recently to existing hypotheses representing previous tasks. The method encourages retention of existing knowledge whilst refining. We analyse the theoretical properties of the proposed framework. Proficiente is accompanied by an agnostic metric that can be used to determine if a long-term learning system is becoming more knowledgeable. We evaluate Proficiente in both synthetic and real-world datasets, and demonstrate scenarios where knowledgeable supervised learning systems can be achieved by means of transfer.

Six keys to unlocking upskilling at scale


These elements have a diverse heritage in learning and management theory, and the way they are implemented will vary from one organization to another. Most or all of them are present, we believe, in every successful effort to raise the caliber of digital skills in an organization. When an initiative is designed effectively, the elements complement one another. Together, these elements create an immersive workplace environment that makes it easy to build new habits and learn new skills, continually reminding people of the progress they've made and the learning yet to come. Just as learning a new language is easier if you move to a community where it is constantly spoken, learning digital proficiency is easier if you are surrounded by other people who are fluent with the relevant technologies. But such widespread fluency is not the situation in businesses today. Training Industry, an organization and information source devoted to "the business of learning," estimates that organizations spent more than $362 billion on employee training and education in 2018 alone, reflecting a growth rate of 1.2 percent per year. Yet as Harvard Business School professor Michael Beer had already pointed out in 2016 in Harvard Business Review, organizations "are not getting a good return on their investment.

Class-Agnostic Continual Learning of Alternating Languages and Domains Artificial Intelligence

Continual Learning has been often framed as the problem of training a model in a sequence of tasks. In this regard, Neural Networks have been attested to forget the solutions to previous task as they learn new ones. Yet, modelling human life-long learning does not necessarily require any crisp notion of tasks. In this work, we propose a benchmark based on language modelling in a multilingual and multidomain setting that prescinds of any explicit delimitation of training examples into distinct tasks, and propose metrics to study continual learning and catastrophic forgetting in this setting. Then, we introduce a simple Product of Experts learning system that performs strongly on this problem while displaying interesting properties, and investigate its merits for avoiding forgetting.

The Big Reboot, Part 1 – Rethinking Education and Employment in an Automated Era Fast Future Publishing


The Big Reboot is a two-part exploration of how we prepare society for the potential impacts of technological disruption, job automation, and the continuing shifts taking place in the global economy. In this first discussion we look at practical strategies for i) raising skills and digital literacy across society, and ii) generating the new ventures and job openings required to fill the employment gap left by those that are displaced by technology. We are reaching peak hysteria in the debate about the potential impact of artificial intelligence (AI) and automation on tasks, roles, jobs, employment, and incomes. On an almost weekly basis, we see projections of wholesale job devastation through automation. These doom-laden forecasts vie with outlandishly optimistic forecasts from AI vendors and consultants suggesting that millions of new roles will be created because of our smart new tech toys.

Random Path Selection for Continual Learning

Neural Information Processing Systems

Incremental life-long learning is a main challenge towards the long-standing goal of Artificial General Intelligence. In real-life settings, learning tasks arrive in a sequence and machine learning models must continually learn to increment already acquired knowledge. The existing incremental learning approaches fall well below the state-of-the-art cumulative models that use all training classes at once. In this paper, we propose a random path selection algorithm, called RPS-Net, that progressively chooses optimal paths for the new tasks while encouraging parameter sharing and reuse. Our approach avoids the overhead introduced by computationally expensive evolutionary and reinforcement learning based path selection strategies while achieving considerable performance gains.

Lifelong Learning with Searchable Extension Units Machine Learning

Lifelong learning remains an open problem. One of its main difficulties is catastrophic forgetting. Many dynamic expansion approaches have been proposed to address this problem, but they all use homogeneous models of predefined structure for all tasks. The common original model and expansion structures ignore the requirement of different model structures on different tasks, which leads to a less compact model for multiple tasks and causes the model size to increase rapidly as the number of tasks increases. Moreover, they can not perform best on all tasks. To solve those problems, in this paper, we propose a new lifelong learning framework named Searchable Extension Units (SEU) by introducing Neural Architecture Search into lifelong learning, which breaks down the need for a predefined original model and searches for specific extension units for different tasks, without compromising the performance of the model on different tasks. Our approach can obtain a much more compact model without catastrophic forgetting. The experimental results on the PMNIST, the split CIFAR10 dataset, the split CIFAR100 dataset, and the Mixture dataset empirically prove that our method can achieve higher accuracy with much smaller model, whose size is about 25-33 percentage of that of the state-of-the-art methods.

2020 and Beyond: Is it Make or Break for AI? Coinspeaker


Once AI has transformed into a lifelong-learning system across industries, individual users and big corporations alike will notice its more than dynamic insights. Artificial Intelligence (AI) in 2020 and beyond, with its seemingly limitless potential, is set to transform the world – or is it? To fully embrace and reap the rewards of this futuristic technological trend, industries as far afield as a business forecasting and online gambling security, predictive maintenance and customer service will need to identify a clear strategy of AI's inherent value for each of them. The answer may lie in AI's many nuances. For example, is your software able to learn new stuff on the fly?

Learning to Continually Learn Machine Learning

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differentiates through a sequential learning process to meta-learn an activation-gating function that enables context-dependent selective activation within a deep neural network. Specifically, a neuromodulatory (NM) neural network gates the forward pass of another (otherwise normal) neural network called the prediction learning network (PLN). The NM network also thus indirectly controls selective plasticity (i.e. the backward pass of) the PLN. ANML enables continual learning without catastrophic forgetting at scale: it produces state-of-the-art continual learning performance, sequentially learning as many as 600 classes (over 9,000 SGD updates).

Detection and Mitigation of Bias in Ted Talk Ratings Artificial Intelligence

Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models. Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined characteristics to members of certain groups and informs the data collection process. This paper quantifies implicit bias in viewer ratings of TEDTalks, a diverse social platform assessing social and professional performance, in order to present the correlations of different kinds of bias across sensitive attributes. Although the viewer ratings of these videos should purely reflect the speaker's competence and skill, our analysis of the ratings demonstrates the presence of overwhelming and predominant implicit bias with respect to race and gender. In our paper, we present strategies to detect and mitigate bias that are critical to removing unfairness in AI.