Learn to build Toxic Question Classifier engine with BERT and TensorFlow 2.4. A Powerful Skill at Your Fingertips Learning the fundamentals of text classification h puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, have excellent documentation. Text classification is a fundamental task in natural language processing (NLP) world. No prior knowledge of word embedding or BERT is assumed.

Good news for folks looking to learn about the latest AI development techniques: Nvidia is now allowing the general public to access the online workshops it provides through its Deep Learning Institute (DLI). The GPU giant today announced today that selected workshops in the DLI catalog will be open to everybody. These workshops previously were available only to companies that wanted specialized training for their in-house developers, or to folks who had attended the company's GPU Technology Conferences. Two of the open courses will take place next month, including "Fundamentals of Accelerated Computing with CUDA Python," which explores developing parallel workloads with CUDA and NumPy and cost $500. There is also "Applications of AI for Predictive Maintenance," which explores technologies like XGBoost, LSTM, Keras, and Tensorflow, and costs $700.

The traditional process of building interactive machine learning systems can be viewed as a teacher-learner interaction scenario where the machine-learners are trained by one or more human-teachers. In this work, we explore the idea of using a conversational interface to investigate the interaction between human-teachers and interactive machine-learners. Specifically, we examine whether teachable AI agents can reliably learn from human-teachers through conversational interactions, and how this learning compare with traditional supervised learning algorithms. Results validate the concept of teachable conversational agents and highlight the factors relevant for the development of machine learning systems that intend to learn from conversational interactions.

iRobot is usually known for their Roomba robot vacuums, but they make coding toys for kids too

Feature-based dynamic pricing is an increasingly popular model of setting prices for highly differentiated products with applications in digital marketing, online sales, real estate and so on. The problem was formally studied as an online learning problem (Cohen et al., 2016; Javanmard & Nazerzadeh, 2019) where a seller needs to propose prices on the fly for a sequence of $T$ products based on their features $x$ while having a small regret relative to the best -- "omniscient" -- pricing strategy she could have come up with in hindsight. We revisit this problem and provide two algorithms (EMLP and ONSP) for stochastic and adversarial feature settings, respectively, and prove the optimal $O(d\log{T})$ regret bounds for both. In comparison, the best existing results are $O\left(\min\left\{\frac{1}{\lambda_{\min}^2}\log{T}, \sqrt{T}\right\}\right)$ and $O(T^{2/3})$ respectively, with $\lambda_{\min}$ being the smallest eigenvalue of $\mathbb{E}[xx^T]$ that could be arbitrarily close to $0$. We also prove an $\Omega(\sqrt{T})$ information-theoretic lower bound for a slightly more general setting, which demonstrates that "knowing-the-demand-curve" leads to an exponential improvement in feature-based dynamic pricing.

Motivated by biological considerations, we study sparse neural maps from an input layer to a target layer with sparse activity, and specifically the problem of storing $K$ input-target associations $(x,y)$, or memories, when the target vectors $y$ are sparse. We mathematically prove that $K$ undergoes a phase transition and that in general, and somewhat paradoxically, sparsity in the target layers increases the storage capacity of the map. The target vectors can be chosen arbitrarily, including in random fashion, and the memories can be both encoded and decoded by networks trained using local learning rules, including the simple Hebb rule. These results are robust under a variety of statistical assumptions on the data. The proofs rely on elegant properties of random polytopes and sub-gaussian random vector variables. Open problems and connections to capacity theories and polynomial threshold maps are discussed.

Algorithmic risk assessments hold the promise of greatly advancing accurate decision-making, but in practice, multiple real-world examples have been shown to distribute errors disproportionately across demographic groups. In this paper, we characterize why error disparities arise in the first place. We show that predictive uncertainty often leads classifiers to systematically disadvantage groups with lower-mean outcomes, assigning them smaller true and false positive rates than their higher-mean counterparts. This can occur even when prediction is group-blind. We prove that to avoid these error imbalances, individuals in lower-mean groups must either be over-represented among positive classifications or be assigned more accurate predictions than those in higher-mean groups. We focus on the latter condition as a solution to bridge error rate divides and show that data acquisition for low-mean groups can increase access to opportunity. We call the strategy "affirmative information" and compare it to traditional affirmative action in the classification task of identifying creditworthy borrowers.

We consider a statistical inverse learning problem, where the task is to estimate a function $f$ based on noisy point evaluations of $Af$, where $A$ is a linear operator. The function $Af$ is evaluated at i.i.d. random design points $u_n$, $n=1,...,N$ generated by an unknown general probability distribution. We consider Tikhonov regularization with general convex and $p$-homogeneous penalty functionals and derive concentration rates of the regularized solution to the ground truth measured in the symmetric Bregman distance induced by the penalty functional. We derive concrete rates for Besov norm penalties and numerically demonstrate the correspondence with the observed rates in the context of X-ray tomography.

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the actions to the task. We propose a task-oriented representation of complex actions, called procedures, to learn online task relationships and unbounded sequences of action primitives to control the different observables of the environment. Combining both goal-babbling with imitation learning, and active learning with transfer of knowledge based on intrinsic motivation, our algorithm self-organises its learning process. It chooses at any given time a task to focus on; and what, how, when and from whom to transfer knowledge. We show with a simulation and a real industrial robot arm, in cross-task and cross-learner transfer settings, that task composition is key to tackle highly complex tasks. Task decomposition is also efficiently transferred across different embodied learners and by active imitation, where the robot requests just a small amount of demonstrations and the adequate type of information. The robot learns and exploits task dependencies so as to learn tasks of every complexity.

Applications for self-regulated teaching are very popular (e.g., with Duolingo estimates of 100M downloads from Google Play at the time of writing). One of the central challenges for research on intelligent user interfaces is to identify algorithmic principles that can pick the best interventions for reliably improving human learning toward stated objectives in light of realistically obtainable data on the user. The computational problem we study is how, when given some learning materials, we can organize them into lessons and reviews such that, over time, human learning is maximized with respect to a set learning objective. Predicting the effects of teaching interventions on human learning is challenging, however. Firstly, the state of user memory is both latent (that is, not directly observable) and non-stationary (that is, evolving over time, on account of such effects as loss of activation and interference), and an intervention that is ideal for one user may be a poor choice for another user -- there are large individual-to-individual differences in forgetting and recall.