Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting. One common limitation of this method is the data imbalance between the previous and current tasks, which would further aggravate forgetting. Moreover, how to effectively address the stability-plasticity dilemma in this setting is also an urgent problem to be solved. In this paper, we overcome these challenges by proposing a novel framework called Meta-learning update via Multi-scale Knowledge Distillation and Data Augmentation (MMKDDA). Specifically, we apply multiscale knowledge distillation to grasp the evolution of long-range and short-range spatial relationships at different feature levels to alleviate the problem of data imbalance. Besides, our method mixes the samples from the episodic memory and current task in the online continual training procedure, thus alleviating the side influence due to the change of probability distribution. Moreover, we optimize our model via the meta-learning update resorting to the number of tasks seen previously, which is helpful to keep a better balance between stability and plasticity. Finally, our experimental evaluation on four benchmark datasets shows the effectiveness of the proposed MMKDDA framework against other popular baselines, and ablation studies are also conducted to further analyze the role of each component in our framework.

Model explainability has become an important problem in machine learning (ML) due to the increased effect that algorithmic predictions have on humans. Explanations can help users understand not only why ML models make certain predictions, but also how these predictions can be changed. In this thesis, we examine the explainability of ML models from three vantage points: algorithms, users, and pedagogy, and contribute several novel solutions to the explainability problem.

Author: Dariusz Trawinski Introduction Model servers play a vital role in bringing AI models from development to production. Models are served via

Streaming videos is one of the methods for creators to share their creative works with their audience. In these videos, the streamer share how they achieve their final objective by using various tools in one or several programs for creative projects. To this end, the steps required to achieve the final goal can be discussed. As such, these videos could provide substantial educational content that can be used to learn how to employ the tools used by the streamer. However, one of the drawbacks is that the streamer might not provide enough details for every step. Therefore, for the learners, it might be difficult to catch up with all the steps. In order to alleviate this issue, one solution is to link the streaming videos with the relevant tutorial available for the tools used in the streaming video. More specifically, a system can analyze the content of the live streaming video and recommend the most relevant tutorials. Since the existing document recommendation models cannot handle this situation, in this work, we present a novel dataset and model for the task of tutorial recommendation for live-streamed videos. We conduct extensive analyses on the proposed dataset and models, revealing the challenging nature of this task.

Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and additional domain knowledge. Simple classical models are useful but sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior. On the other hand, purely data-driven approaches that are model-agnostic are becoming increasingly popular as datasets become abundant and the power of modern deep learning pipelines increases. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance, especially for supervised problems. However, DNNs typically require massive amounts of data and immense computational resources, limiting their applicability for some signal processing scenarios. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches. Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data. In this article we survey the leading approaches for studying and designing model-based deep learning systems. We divide hybrid model-based/data-driven systems into categories based on their inference mechanism. We provide a comprehensive review of the leading approaches for combining model-based algorithms with deep learning in a systematic manner, along with concrete guidelines and detailed signal processing oriented examples from recent literature. Our aim is to facilitate the design and study of future systems on the intersection of signal processing and machine learning that incorporate the advantages of both domains.

Beginners Guide to Implementing Neural Networks with Keras In this course, you will learn how to implement all major kinds of neural networks with hands-on projects in Keras .

A semantic tableau method, called an argumentation tableau, that enables the derivation of arguments, is proposed. First, the derivation of arguments for standard propositional and predicate logic is addressed. Next, an extension that enables reasoning with defeasible rules is presented. Finally, reasoning by cases using an argumentation tableau is discussed.

In this course, you will learn how to implement all major kinds of neural networks with hands-on projects in Keras. For each of the projects, code is provided and Colab notebooks are shared which you can experiment with. This course is designed in a way to get started from the very basics and then reach a stage where you will be able to implement very recent and complex models. It is expected that you already have a theoretical background in deep learning a very basic knowledge would be enough to get started with this course. Hope you will like the course and will enjoy following it.

In traditional programming, a computer engineer writes a series of directions that instruct a computer how to transform input data into a desired output. Machine learning, on the other hand, is an automated process that enables machines to solve problems with little or no human input, and take actions based on past observations. In this course we are going to talk about the basics of the machine learning which will provide a strong foundation to the students who want to make a career in the field of data sciences and machine learning, we will go through each of the basic important thing that a beginner needs to know to get started with machine learning. We will be talking about what is the machine learning and why exactly we need to use the machine learning, then we will discuss the types of the machine learning system where we will be going in detail about all type and classification of the machine learning system. Then we will talk about the main problems that the data scientist face when they perform machine learning task or making a machine learning algorithm.

M47AI is a fast growing Barcelona based tech company with a focus on providing outstanding international data analytics services. We may be a newer company, but our deep knowledge and strong industry experience allows us to work with top companies around the world. We are offering an internship position to join our team as a Data Annotator. You will participate in a big Data Annotation project for text which will help the use of Catalan in the AI space. Your annotations will be the base to train Machine Learning and Natural Language Processing algorithms!