We introduce two methods for improving the performance of agents meeting for the first time to accomplish a communicative task. The methods are: (1) `message mutation' during the generation of the communication protocol; and (2) random permutations of the communication channel. These proposals are tested using a simple two-player game involving a `teacher' who generates a communication protocol and sends a message, and a `student' who interprets the message. After training multiple agents via self-play we analyse the performance of these agents when they are matched with a stranger, i.e. their zero-shot communication performance. We find that both message mutation and channel permutation positively influence performance, and we discuss their effects.

While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on contrastive learning to train the network and in this work, we propose a simple yet effective Distilled Contrastive Learning (DisCo) to ease the issue by a large margin. Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher. In addition, in the experiment, we find that there exists a phenomenon termed Distilling BottleNeck and present to enlarge the embedding dimension to alleviate this problem. Our method does not introduce any extra parameter to lightweight models during deployment. Experimental results demonstrate that our method achieves the state-of-the-art on all lightweight models. Particularly, when ResNet-101/ResNet-50 is used as teacher to teach EfficientNet-B0, the linear result of EfficientNet-B0 on ImageNet is very close to ResNet-101/ResNet-50, but the number of parameters of EfficientNet-B0 is only 9.4%/16.3% of ResNet-101/ResNet-50.

Artificial intelligence has entered every industry, and the educational sector is no exception. The administrative staff, management, teachers, and students are all using AI in different ways to achieve similar goals. During the last few years, AI has spread its roots much wider and deeper in this sector. Markets and Markets has predicted that the global market share of AI in education is estimated to reach $3.68 billion by 2023 at a CAGR (Compound Annual Growth Rate) of 47%. Another platform, Market Search Engine, has predicted that the share will reach $5.80 billion by 2025.

Two years ago, computer science professor Dr. Meena Vimal Cruz handed her student Matthew Pittendreigh a project: use artificial intelligence (AI) and natural language processing to create a chatbot for the college. "In my teaching," said Dr. Cruz, "I mentor students and help them get hands-on experience, applying theoretical knowledge to real-world problems. We work on a project basis. A chatbot will act like an automated customer support to help prospective students apply, get connected, and answer important questions about resources and deadlines, any hour of the day or night." Matthew, already a veteran of Dr. Cruz's projects, jumped right in.

GUVI has joined hands with AICTE to offer free online training for Artificial Intelligence professionals or students. AICTE with the partnership with GUVI is offering free online Artificial Intelligence to the participants that will be a 90 minutes workshop. The event will start from April 24 2021 6 PM IST to April 25 2021 at 6 PM IST in different time slots for participants. The aim behind the event is to help the students to polish their Python skills and develop the face recognition app. The training is an initiative taken by AICTE and GUVI to help the professionals of India to top the Artificial Intelligence domain.

Education is the basic step of understanding the truth and the preparation of the intelligence to reflect. Focused on the rational capacity of the human being the Cognitive process and knowledge dimensions of Revised Blooms Taxonomy helps to differentiate the procedure of studying into six types of various cognitive processes and four types of knowledge dimensions. These types are synchronized in the increasing level of difficulty. In this paper Software Engineering courses of B.Tech Computer Engineering and Information Technology offered by various Universities and Educational Institutes have been investigated for Revised Blooms Taxonomy RBT. Questions are a very useful constituent. Knowledge intelligence and strength of the learners can be tested by applying questions.The fundamental goal of this paper is to create a relative study of the classification of the summative assessment based on Revised Blooms Taxonomy using the Convolutional Neural Networks CNN Long Short-Term Memory LSTM of Deep Learning techniques in an endeavor to attain significant accomplishment and elevated precision levels.

Increasing concerns and regulations about data privacy, necessitate the study of privacy-preserving methods for natural language processing (NLP) applications. Federated learning (FL) provides promising methods for a large number of clients (i.e., personal devices or organizations) to collaboratively learn a shared global model to benefit all clients, while allowing users to keep their data locally. To facilitate FL research in NLP, we present the FedNLP, a research platform for federated learning in NLP. FedNLP supports various popular task formulations in NLP such as text classification, sequence tagging, question answering, seq2seq generation, and language modeling. We also implement an interface between Transformer language models (e.g., BERT) and FL methods (e.g., FedAvg, FedOpt, etc.) for distributed training. The evaluation protocol of this interface supports a comprehensive collection of non-IID partitioning strategies. Our preliminary experiments with FedNLP reveal that there exists a large performance gap between learning on decentralized and centralized datasets -- opening intriguing and exciting future research directions aimed at developing FL methods suited to NLP tasks.

We propose a new general training technique for attention mechanisms based on virtual adversarial training (VAT). VAT can compute adversarial perturbations from unlabeled data in a semi-supervised setting for the attention mechanisms that have been reported in previous studies to be vulnerable to perturbations. Empirical experiments reveal that our technique (1) provides significantly better prediction performance compared to not only conventional adversarial training-based techniques but also VAT-based techniques in a semi-supervised setting, (2) demonstrates a stronger correlation with the word importance and better agreement with evidence provided by humans, and (3) gains in performance with increasing amounts of unlabeled data.

It is often challenging for a system to solve a new complex problem from scratch, but much easier if the system can access other similar problems and description of their solutions -- a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach for question answering over large knowledge bases (CBR-KBQA). While the idea of CBR is tempting, composing a solution from cases is nontrivial, when individual cases only contain partial logic to the full solution. To resolve this, CBR-KBQA consists of two modules: a non-parametric memory that stores cases (question and logical forms) and a parametric model which can generate logical forms by retrieving relevant cases from memory. Through experiments, we show that CBR-KBQA can effectively derive novel combination of relations not presented in case memory that is required to answer compositional questions. On several KBQA datasets that test compositional generalization, CBR-KBQA achieves competitive performance. For example, on the challenging ComplexWebQuestions dataset, CBR-KBQA outperforms the current state of the art by 11% accuracy. Furthermore, we show that CBR-KBQA is capable of using new cases \emph{without} any further training. Just by incorporating few human-labeled examples in the non-parametric case memory, CBR-KBQA is able to successfully generate queries containing unseen KB relations.

Udacity is one of the most popular MOOC-based e-learning platforms in the world. Udacity has a wide range of machine learning and data science courses. Some are free and some are paid. But in this article, I am gonna discuss all the Udacity FREE Courses on Machine Learning and Data Science. For these courses, You don't need to pay a single buck.