The next wave of on-device AI will likely require energy-efficient deep neural networks. Brain-inspired spiking neural networks (SNN) has been identified to be a promising candidate. Doing away with the need for multipliers significantly reduces energy. For on-device applications, besides computation, communication also incurs a significant amount of energy and time. In this paper, we propose Shenjing, a configurable SNN architecture which fully exposes all on-chip communications to software, enabling software mapping of SNN models with high accuracy at low power. Unlike prior SNN architectures like TrueNorth, Shenjing does not require any model modification and retraining for the mapping. We show that conventional artificial neural networks (ANN) such as multilayer perceptron, convolutional neural networks, as well as the latest residual neural networks can be mapped successfully onto Shenjing, realizing ANNs with SNN's energy efficiency. For the MNIST inference problem using a multilayer perceptron, we were able to achieve an accuracy of 96% while consuming just 1.26mW using 10 Shenjing cores.

The topic of provable deep neural network robustness has raised considerable interest in recent years. Most research has focused on adversarial robustness, which studies the robustness of perceptive models in the neighbourhood of particular samples. However, other works have proved global properties of smaller neural networks. Yet, formally verifying perception remains uncharted. This is due notably to the lack of relevant properties to verify, as the distribution of possible inputs cannot be formally specified. We propose to take advantage of the simulators often used either to train machine learning models or to check them with statistical tests, a growing trend in industry. Our formulation allows us to formally express and verify safety properties on perception units, covering all cases that could ever be generated by the simulator, to the difference of statistical tests which cover only seen examples. Along with this theoretical formulation , we provide a tool to translate deep learning models into standard logical formulae. As a proof of concept, we train a toy example mimicking an autonomous car perceptive unit, and we formally verify that it will never fail to capture the relevant information in the provided inputs.

In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms.

Human conversations in real scenarios are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context. It also covers various dialogue types including task-oriented, chitchat and question-answering. Extra intent information and three well-annotated challenge sets are also provided. Then, we evaluate several retrieval-based and generative models to provide basic benchmark performance on JDDC corpus. And we hope JDDC can serve as an effective testbed and benefit the development of fundamental research in dialogue task.

To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.

Data Science is definitely one of the hottest market right now. Almost every company has a data science positions opened or is thinking about one. That means it's the best time to become a Data Scientist or hone your skills if you're already one and want to level up to more senior positions. This text covers some of the most popular books on Data Science. If you're just starting your adventure with Data Science, you should definitely try: Data Science from Scratch is what the name suggest: an introduction to Data Science for total beginners.

Although Computer Vision (CV) has only exploded recently (the breakthrough moment happened in 2012 when AlexNet won ImageNet), it certainly isn't a new scientific field. Computer scientists around the world have been trying to find ways to make machines extract meaning from visual data for about 60 years now, and the history of Computer Vision, which most people don't know much about, is deeply fascinating. In this article, I'll try to shed some light on how modern CV systems, powered primarily by convolutional neural networks, came to be. I'll start with a work that came out in the late 1950s and has nothing to do with software engineering or software testing. One of the most influential papers in Computer Vision was published by two neurophysiologists -- David Hubel and Torsten Wiesel -- in 1959.

Artificial Neural Networks – As the name suggest "Neural Network", they are inspired by the human brain system. ANNs were originally designed with biological neurons as a reference point thus sometimes they are called a brain model for computers. ANNs can process information in form audio, video, images, texts, numbers or in any form of data. Neurons i.e. perceptrons (as known in early days) were staged as a decision function in those times. Artificial Neural networks are designed to take several binary inputs to give a binary output. Professor Frank Rosenblatt was the first one to use neural networks.

Design and build personalization engines/learning systems using advanced machine learning and statistical techniques Help the company in identifying tools and components, and building the infrastructure for AI/ML Research and brainstorm with internal partners to identify advanced analytics opportunities to advance automation, help with knowledge discovery, support decision-making, gain insights from data, streamline business processes, and enable new capabilities Perform hands-on data exploration and modeling work on massive data sets. Perform feature engineering, train the algorithms, back-test models, compare model performances and communicate the results Work with senior leaders from all functions to explore opportunities for using advance analytics Provide technical leadership mentoring to talented data scientists and analytics professionals Guide data scientists and engineers in the use of advanced statistical, machine learning, and artificial intelligence methodologies Provide thought leadership by researching best practices, extending and building new machine learning and statistical methodologies, conducting experiments, and collaborating with cross functional teams Develop end-to-end efficient model solutions that drive measurable outcomes. These technical skills include, but not limited to, regression techniques, neural networks, decision trees, clustering, pattern recognition, probability theory, stochastic systems, Bayesian inference, statistical techniques, deep learning, supervised learning, unsupervised learning Solid understanding and hands on experience working with big data, and the related ecosystem, both relational and unstructured. Executing on complex projects, extracting, cleansing, and manipulating large, diverse structured and unstructured data sets on relational – SQL, NOSQL databases Working in an agile environment with iterative development & business feedback Providing insights to support strategic decisions, including offering and delivering insights and recommendations Experience in statistics & analytical modeling, time-series data analysis, forecasting modeling, machine learning algorithms, and deep learning approaches and frameworks. Deliver robust, scale and quality data analytical applications in a cloud environment.

Word embeddings have revolutionized the world of natural language processing(NLP). Conceptually, word embeddings are language modeling methods that map phrases or words in a sentence to vectors and numbers. One of the first steps in any NLP application is to determine what type of word embedding algorithm is going to be used. Typically, NLP models resort to pretrained word embedding algorithm such as Word2Vec, Glove or FastText. While that approach is relatively simple, it also results highly inefficient as is near to impossible to determine what word embedding will perform better as the NLP model evolves.