Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. The theory of f-formation can be utilized for this purpose. As the types of formations can be very diverse, detecting the social groups is not a trivial task. In this article, we provide a comprehensive survey of the existing work on social interaction and group detection using f-formation for robotics and other applications. We also put forward a novel holistic survey framework combining all the possible concerns and modules relevant to this problem. We define taxonomies based on methods, camera views, datasets, detection capabilities and scale, evaluation approaches, and application areas. We discuss certain open challenges and limitations in current literature along with possible future research directions based on this framework. In particular, we discuss the existing methods/techniques and their relative merits and demerits, applications, and provide a set of unsolved but relevant problems in this domain.

Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or time critical inference applications. State-of-the-art (SOTA) approaches focus on post-training quantization, i.e. quantization of pre-trained DNNs for speeding up inference. Little work on quantized training exists and usually, existing approaches re-quire full precision refinement afterwards or enforce a global word length across the whole DNN. This leads to suboptimal bitwidth-to-layers assignments and re-source usage. Recognizing these limits, we introduce ADEPT, a new quantized sparsifying training strategy using information theory-based intra-epoch precision switching to find on a per-layer basis the lowest precision that causes no quantization-induced information loss while keeping precision high enough for future learning steps to not suffer from vanishing gradients, producing a fully quantized DNN. Based on a bitwidth-weighted MAdds performance model, our approach achieves an average speedup of 1.26 and model size reduction of 0.53 compared to standard training in float32 with an average accuracy increase of 0.98% on AlexNet/ResNet on CIFAR10/100.

Linear regression is a regression model which tries to predict the relationship between the dependent variable Y and independent variable X in a linear fashion. It is a regression models which mean that it is used to predict continuous values. Standard Scalar transforms the data in such a manner where mean 0 and SD 1, which is standard normal distribution. How does standard scalar effects testing data? If we have reached the minimum number of features threshold. Low score is due to spread of values and skewness in the predictive column.

A quick and easy to follow tutorial on the method of Lagrange multipliers when finding the local minimum of a function subject to equality constraints.

In this blog, first of all we will see what is K-Means Clustering Algorithm and then discuss about some of it's Industry use-cases. Unsupervised learning is a type of machine learning in which models are trained using unlabeled dataset and are allowed to act on that data without any supervision. Unsupervised learning cannot be directly applied to a regression or classification problem because unlike supervised learning, we have the input data but no corresponding output data. The goal of unsupervised learning is to find the underlying structure of dataset, group that data according to similarities, and represent that dataset in a compressed format. K-Means Clustering is an Unsupervised Learning algorithm, which groups the unlabeled dataset into different clusters.

One of the most popular Machine Learning algorithms is K-means clustering. It is an unsupervised learning algorithm, meaning that it is used for unlabeled datasets. K-means clustering algorithm is an unsupervised technique to group data in the order of their similarities. We then find patterns within this data which are present as k-clusters. Each of the n value belongs to the k cluster with the nearest mean.

Before implementing a project, it's best to understand a few fundamental concepts on Object Detection and how it works together. Let's start by defining Object Detection: Image classification is where an algorithm is applied to an image to predict the class of one object eg: Car. Object localization not only predicts the class of objects but also figures out the location of the object by drawing a bounding box around the object. Object detection involves both classification and localization and detects more than one object & more than one class even. A standard classification task would involve an image running through a Convnet with multiple layers in which vector features are fed into a softmax unit for example that outputs the predicted class (Object categories that the algorithm is trying to detect i.e cars, trees, pedestrians).

I will write a series of short articles to illustrate how to implement ML codes from scratch and also introduce the algorithm’s pros and cons in short. It can be considered as the probability of…

Since I was in high school, I've had this weird obsession of squeeze the key concepts of everything that I learn in one page. Looking back, that was probably my lazy mind's way to get away with the least amount of required work to pass an exam…but interestingly that abstraction effort also helped a lot to learn those concepts in a deeper level and to remember them longer. Nowadays when I teach Machine Learning, I try to teach it in two parallel tracks: a) main concepts and b) methods and theoretical details, and make sure my students can look at each new method through the lens of the same concepts. Recently I got a chance to read "Machine Learning Yearning" by Andrew Ng, which seemed to be his version of abstracting some of the practical ML concepts without getting into any formula or implementation details. While they can see so simple and obvious, as an ML engineer I can attest that losing sight of those simple tips are among the most common causes for an ML research to fail in production, and being mindful of them is what distinguishes a good data science work from a mediocre one.

The process of mastering new knowledge often requires multiple passes to ensure the information is deeply understood. If you already began your journey into machine learning and data science, then you are likely ready for a refresher on topics you previously covered. This eight-week self-learning path will help you recapture…