But the story is bigger than just using quantum computers to tackle machine learning problems. Quantum circuits are differentiable, and a quantum computer itself can compute the change in control parameters needed to become better at a given task. Differentiable programming is the very basis of deep learning, implemented in software libraries such as TensorFlow and PyTorch. Differentiable programming is more than deep learning: it is a programming paradigm where the algorithms are not hand-coded, but learned. Similarly, the idea of training quantum computers is larger than quantum machine learning.

Darren Oberst, Senior Corporate Vice President and Global Head of HCL Software, joins Innodata's Podcast, Absolute AI, as a guest on the topic, Conversations With the Humans Behind Artificial Intelligence. Darren discusses how he transformed his lifelong passion into a career in international leadership. At 10 years old, Darren learned to program. He wrote computer games, sold them to friends and even wrote his own computer language. As a techie at heart and a machine learning hobbyist, he eventually moved to the business side.

How can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find evidences indicating that the adaptations of PLMs to various tasks can be reparameterized as optimizing only a few free parameters in a common low-dimensional intrinsic task subspace, which may help us understand why PLMs could easily adapt to various NLP tasks with small-scale data. Specifically, to find such a subspace and examine its universality, we resort to the recent success of prompt tuning and decompose the soft prompts of multiple NLP tasks into the same low-dimensional nonlinear subspace, then we learn to adapt the PLM to unseen tasks or data by only tuning parameters in the subspace. We dub this pipeline as intrinsic prompt tuning (IPT). In experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 5-dimensional subspace found with 100 random tasks, by only tuning 5 free parameters, we can recover 87% and 65% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace. Besides being an analysis tool, IPT could further bring practical benefits, such as improving the prompt tuning stability.

As student failure rates continue to increase in higher education, predicting student performance in the following semester has become a significant demand. Personalized student performance prediction helps educators gain a comprehensive view of student status and effectively intervene in advance. However, existing works scarcely consider the explainability of student performance prediction, which educators are most concerned about. In this paper, we propose a novel Explainable Student performance prediction method with Personalized Attention (ESPA) by utilizing relationships in student profiles and prior knowledge of related courses. The designed Bidirectional Long Short-Term Memory (BiLSTM) architecture extracts the semantic information in the paths with specific patterns. As for leveraging similar paths' internal relations, a local and global-level attention mechanism is proposed to distinguish the influence of different students or courses for making predictions. Hence, valid reasoning on paths can be applied to predict the performance of students. The ESPA consistently outperforms the other state-of-the-art models for student performance prediction, and the results are intuitively explainable. This work can help educators better understand the different impacts of behavior on students' studies.

In the last few years, Deep Learning models have become increasingly popular. However, their deployment is still precluded in those contexts where the amount of supervised data is limited and manual labelling expensive. Active learning strategies aim at solving this problem by requiring supervision only on few unlabelled samples, which improve the most model performances after adding them to the training set. Most strategies are based on uncertain sample selection, and even often restricted to samples lying close to the decision boundary. Here we propose a very different approach, taking into consideration domain knowledge. Indeed, in the case of multi-label classification, the relationships among classes offer a way to spot incoherent predictions, i.e., predictions where the model may most likely need supervision. We have developed a framework where first-order-logic knowledge is converted into constraints and their violation is checked as a natural guide for sample selection. We empirically demonstrate that knowledge-driven strategy outperforms standard strategies, particularly on those datasets where domain knowledge is complete. Furthermore, we show how the proposed approach enables discovering data distributions lying far from training data. Finally, the proposed knowledge-driven strategy can be also easily used in object-detection problems where standard uncertainty-based techniques are difficult to apply.

Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for a revisit. In this paper, we present Broad-persistent Advising (BPA), a broad-persistent advising approach that retains and reuses the processed information. It not only helps trainers to give more general advice relevant to similar states instead of only the current state but also allows the agent to speed up the learning process. We test the proposed approach in two continuous robotic scenarios, namely, a cart pole balancing task and a simulated robot navigation task. The obtained results show that the performance of the agent using BPA improves while keeping the number of interactions required for the trainer in comparison to the DeepIRL approach.

Deep reinforcement learning has shown its effectiveness in various applications and provides a promising direction for solving tasks with high complexity. In most reinforcement learning algorithms, however, two major issues need to be dealt with - the sample inefficiency and the interpretability of a policy. The former happens when the environment is sparsely rewarded and/or has a long-term credit assignment problem, while the latter becomes a problem when the learned policies are deployed at the customer side product. In this paper, we propose a novel hierarchical reinforcement learning algorithm that mitigates the aforementioned issues by decomposing the original task in a hierarchy and by compounding pretrained primitives with intents. We show how the proposed scheme can be employed in practice by solving a pick and place task with a 6 DoF manipulator.

In this paper, we develop a new type of accelerated algorithms to solve some classes of maximally monotone equations as well as monotone inclusions. Instead of using Nesterov's accelerating approach, our methods rely on a so-called Halpern-type fixed-point iteration in [32], and recently exploited by a number of researchers, including [24, 70]. Firstly, we derive a new variant of the anchored extra-gradient scheme in [70] based on Popov's past extra-gradient method to solve a maximally monotone equation $G(x) = 0$. We show that our method achieves the same $\mathcal{O}(1/k)$ convergence rate (up to a constant factor) as in the anchored extra-gradient algorithm on the operator norm $\Vert G(x_k)\Vert$, , but requires only one evaluation of $G$ at each iteration, where $k$ is the iteration counter. Next, we develop two splitting algorithms to approximate a zero point of the sum of two maximally monotone operators. The first algorithm originates from the anchored extra-gradient method combining with a splitting technique, while the second one is its Popov's variant which can reduce the per-iteration complexity. Both algorithms appear to be new and can be viewed as accelerated variants of the Douglas-Rachford (DR) splitting method. They both achieve $\mathcal{O}(1/k)$ rates on the norm $\Vert G_{\gamma}(x_k)\Vert$ of the forward-backward residual operator $G_{\gamma}(\cdot)$ associated with the problem. We also propose a new accelerated Douglas-Rachford splitting scheme for solving this problem which achieves $\mathcal{O}(1/k)$ convergence rate on $\Vert G_{\gamma}(x_k)\Vert$ under only maximally monotone assumptions. Finally, we specify our first algorithm to solve convex-concave minimax problems and apply our accelerated DR scheme to derive a new variant of the alternating direction method of multipliers (ADMM).

I do really appreciate these helpful on-hand labs and lectures. Passed the DP-100 in Dec 2020.

HANSON: They've had a chequered past, I'll give you that. The Egyptians seemed to be confusing them for some kind of Gods at some point.