Interleaving learning is a human learning technique where a learner interleaves the studies of multiple topics, which increases long-term retention and improves ability to transfer learned knowledge. Inspired by the interleaving learning technique of humans, in this paper we explore whether this learning methodology is beneficial for improving the performance of machine learning models as well. We propose a novel machine learning framework referred to as interleaving learning (IL). In our framework, a set of models collaboratively learn a data encoder in an interleaving fashion: the encoder is trained by model 1 for a while, then passed to model 2 for further training, then model 3, and so on; after trained by all models, the encoder returns back to model 1 and is trained again, then moving to model 2, 3, etc. This process repeats for multiple rounds. Our framework is based on multi-level optimization consisting of multiple inter-connected learning stages. An efficient gradient-based algorithm is developed to solve the multi-level optimization problem. We apply interleaving learning to search neural architectures for image classification on CIFAR-10, CIFAR-100, and ImageNet. The effectiveness of our method is strongly demonstrated by the experimental results.

Building a socially intelligent agent involves many challenges, one of which is to track the agent's mental state transition and teach the agent to make rational decisions guided by its utility like a human. Towards this end, we propose to incorporate a mental state parser and utility model into dialogue agents. The hybrid mental state parser extracts information from both the dialogue and event observations and maintains a graphical representation of the agent's mind; Meanwhile, the utility model is a ranking model that learns human preferences from a crowd-sourced social commonsense dataset, Social IQA. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (\textit{i}) how the proposed mental state parser can assist agent's decision by grounding on the context like locations and objects, and (\textit{ii}) how the utility model can help the agent make reasonable decisions in a dilemma. To the best of our knowledge, we are the first work that builds a socially intelligent agent by incorporating a hybrid mental state parser for both discrete events and continuous dialogues parsing and human-like utility modeling.

In human learning, an effective skill in improving learning outcomes is learning by teaching: a learner deepens his/her understanding of a topic by teaching this topic to others. In this paper, we aim to borrow this teaching-driven learning methodology from humans and leverage it to train more performant machine learning models, by proposing a novel ML framework referred to as learning by teaching (LBT). In the LBT framework, a teacher model improves itself by teaching a student model to learn well. Specifically, the teacher creates a pseudo-labeled dataset and uses it to train a student model. Based on how the student performs on a validation dataset, the teacher re-learns its model and re-teaches the student until the student achieves great validation performance. Our framework is based on three-level optimization which contains three stages: teacher learns; teacher teaches student; teacher re-learns based on how well the student performs. A simple but efficient algorithm is developed to solve the three-level optimization problem. We apply LBT to search neural architectures on CIFAR-10, CIFAR-100, and ImageNet. The efficacy of our method is demonstrated in various experiments.

This paper focuses on a class of reinforcement learning problems where significant events are rare and limited to a single positive reward per episode. A typical example is that of an agent who has to choose a partner to cooperate with, while a large number of partners are simply not interested in cooperating, regardless of what the agent has to offer. We address this problem in a continuous state and action space with two different kinds of search methods: a gradient policy search method and a direct policy search method using an evolution strategy. We show that when significant events are rare, gradient information is also scarce, making it difficult for policy gradient search methods to find an optimal policy, with or without a deep neural architecture. On the other hand, we show that direct policy search methods are invariant to the rarity of significant events, which is yet another confirmation of the unique role evolutionary algorithms has to play as a reinforcement learning method.

Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose an adaptive attack method with better attack performance. Furthermore, we modify the conventional federated reinforcement learning algorithm to address the issue of adversaries that works equally well with and without the adversaries. Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents.

A couple of days ago I started thinking if I had to start learning machine learning and data science all over again where would I start? The funny thing was that the path that I imagined was completely different from that one that I actually did when I was starting. I'm aware that we all learn in different ways. Some prefer videos, others are ok with just books and a lot of people need to pay for a course to feel more pressure. And that's ok, the important thing is to learn and enjoy it.

The significance of artificial intelligence and machine learning (AIML) has increased by much in technology in recent years. It has gone to a point where they are helping businesses gain an advantage over their competitors. With the ever-increasing volumes of data generated each day, it becomes essential to process it in real-time. This is where AIML comes into the picture as the technology can help process and analyze volumes of data within minutes. The relevance of IoT devices, too, has been on the rise.

By Arnuld OnData, Industrial Software Developer turned Data Scientist. There is one thing you need to focus on first: how much math for data science. Learning Statistics was very confusing. I could not connect different parts of the topics. I took a STAT100 from Penn State online (a week), and I still could not remember anything.

Artificial intelligence (AI) is already embedded in a range of digital services. Voice assistants such as Alexa, car routing or content translation all involve machine learning – the most popular form of artificial intelligence technology. There are many warnings these days about AI, such as the ethics behind these machine driven decision systems or threats of automation and the loss of many jobs. Very little is reported about how artificial intelligence can improve public services and can have positive social impact. Smart algorithms combined with cloud computing power allow unprecedented forms of data analysis that would take much longer if humans were doing it.

Computer science degrees are a good choice for students as the range of roles open to graduates continues to grow. From supporting IT infrastructure at a company, to creating apps or to working in banks and financial services, there is a huge range of paths available to computer science graduates. The UK is home to some of the most prestigious universities in the world, many of which are involved at the cutting edge of computer science research and are bolstered by a steady stream of dedicated grants and funding. There are full-time, part-time and flexible-study options, as well as courses with a placement year in industry, known as sandwich courses. Below are the best universities in the UK for computer science degrees.