Spiking neural networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs). The design of training algorithms lags behind the hardware implementations. Most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding. This article provides an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules by leveraging the unique time-encoding capabilities of SNNs. We adopt discrete-time probabilistic models for networked spiking neurons and derive supervised and unsupervised learning rules from first principles via variational inference. Examples and open research problems are also provided.

Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. During model selection and debugging, data scientists need to asses classifier performance, evaluate the training behavior over time, and compare different models. Typically, this analysis is based on single-number performance measures such as accuracy. A more detailed evaluation of classifiers is possible by inspecting class errors. The confusion matrix is an established way for visualizing these class errors, but it was not designed with temporal or comparative analysis in mind. More generally, established performance analysis systems do not allow a combined temporal and comparative analysis of class-level information. To address this issue, we propose ConfusionFlow, an interactive, comparative visualization tool that combines the benefits of class confusion matrices with the visualization of performance characteristics over time. ConfusionFlow is model-agnostic and can be used to compare performances for different model types, model architectures, and/or training and test datasets. We demonstrate the usefulness of ConfusionFlow in the context of two practical problems: an analysis of the influence of network pruning on model errors, and a case study on instance selection strategies in active learning.

Inverse reinforcement learning (IRL) is used to infer the reward function from the actions of an expert running a Markov Decision Process (MDP). A novel approach using variational inference for learning the reward function is proposed in this research. Using this technique, the intractable posterior distribution of the continuous latent variable (the reward function in this case) is analytically approximated to appear to be as close to the prior belief while trying to reconstruct the future state conditioned on the current state and action. The reward function is derived using a well-known deep generative model known as Conditional Variational Auto-encoder (CVAE) with Wasserstein loss function, thus referred to as Conditional Wasserstein Auto-encoder-IRL (CWAE-IRL), which can be analyzed as a combination of the backward and forward inference. This can then form an efficient alternative to the previous approaches to IRL while having no knowledge of the system dynamics of the agent. Experimental results on standard benchmarks such as objectworld and pendulum show that the proposed algorithm can effectively learn the latent reward function in complex, high-dimensional environments.

The talk is Wednesday afternoon, Jan. 30. Here is the paper: Envisioning AI for K-12: What should every child know about AI?

When I say Artificial Intelligence (AI), what comes to mind? Chances are that it's something about robots taking over the world. That's what I thought of the first time I started learning about it just a few years ago. But as I dove deeper into how AI really works, on both a programming and even somewhat of a mathematical level, I realized that AI is nothing like that, and yet so much more. First, let's clear something up.

In today's connected world, factories are smart, cars are smart, buildings are smart, and homes are smart. School campuses should be smart too. The number of gun-violence incidents in the United States is much too high, and while politicians and special interest groups argue about how exactly to curb this violence, technology could help keep campuses safer. The latest IoT (Internet of Things) technologies could streamline campus and school operations to help them run as efficiently as possible. According to MarketsandMarkets, the global IoT in education market is expected to grow from $4.8 billion in 2018 to $11.3 billion by 2023.

Below is the 15 best machine learning course to accelerate your ML journey this year. The holy grail of machine learning online course, Machine Learning by Stanford is considered as the best machine learning course by many. This course is prepared and maintained by Andrew Ng, pioneer machine learning scientist who've led ML research projects for both Google and Chinese giant Baidu. Although the course requires a paid subscription, you can ask for financial aid if you're a student. This online machine learning course from DataCamp is the best machine learning course with a primary emphasis on statistics – the de facto requirement for effective data science projects.

Welcome to the Complete Data Science and Machine Learning Bootcamp, the only course you need to learn Python and get into data science. At over 35 hours, this Python course is without a doubt the most comprehensive data science and machine learning course available online. Even if you have zero programming experience, this course will take you from beginner to mastery. The course is a taught by the lead instructor at the App Brewery, London's leading in-person programming bootcamp. In the course, you'll be learning the latest tools and technologies that are used by data scientists at Google, Amazon, or Netflix.

Amazon rolled out more than a dozen new devices today in its annual hardware event atop a biodome at company headquarters in Seattle, including eyeglasses and a ring that speak with Alexa, several new speakers, and lots of new devices for the home. Sprinkled in between hardware announcements were a bunch of new ways Alexa is getting smarter. In all, like last year, nearly a dozen new features were introduced today. Here are some of the standouts. One unique offering introduced today is the Education Skills API, a way for skills developers and school districts to connect with popular edtech services like Canvas, Kickboard, and Coursera.

Designing deep learning systems is hard and highly subjective. Any midsize neural network could contain millions of nodes and hundreds of hidden layers. Given a specific deep learning problem, there is a large number of possible neural network architectures that can serve as a solution. Typically, we need to rely on the expertise or subjective preferences of data scientists to settle on a specific approach but that seems highly unpractical. Recently, neural architecture search(NAS) has emerged as an alternative solution to this problem by making the design of deep learning systems a machine learning problem by itself.