The simple image captured in camera consists colors of different wavelengths (visible spectrum) which can be represented with combination of three colors — Red,Green and Blue (RGB). Thus digital…

Human beings so easily perceive the visual surroundings, it doesn't require any effort. It is like instantly interpreting the visual information we see without even being bothered as to how we understand? But making machines see is not easy and requires a lot of work. Lots of research and efforts have been undertaken and are ongoing to make the systems understand the visual inputs just like human beings. Computer vision (CV) is a field of AI that provides the capability to the devices to interpret visual inputs like images and videos.

Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force misclassification by an otherwise high performing neural network. To have a better understanding of the key contributors of such structured attacks, we searched for and studied spatially co-located patterns in the distribution of pixels in the input space. In this paper, we propose a framework for segregating and isolating regions within an input image which are particularly critical towards either classification (during inference), or adversarial vulnerability or both. We assert that during inference, the trained model looks at a specific region in the image, which we call Region of Importance (RoI); and the attacker looks at a region to alter/modify, which we call Region of Attack (RoA). The success of this approach could also be used to design a post-hoc adversarial defence method, as illustrated by our observations. This uses the notion of blocking out (we call neutralizing) that region of the image which is highly vulnerable to adversarial attacks but is not important for the task of classification. We establish the theoretical setup for formalising the process of segregation, isolation and neutralization and substantiate it through empirical analysis on standard benchmarking datasets. The findings strongly indicate that mapping features into the input space preserves the significant patterns typically observed in the feature-space while adding major interpretability and therefore simplifies potential defensive mechanisms.

The first issue of image analysis is classification. The problem is that we get a picture at the input and we want to get information at the output. The classification is defined by assigning an object to a group of objects called a class. It assumes that we have a group of objects and assign them to classes at the same time. Each object should be characterized by appropriate features: shape, color, proportions of different characteristic sizes. In order to assign an object to a particular class, it is necessary to find a set of features that can be found automatically in the image.

CNN's have been extensively used to classify images. But to detect an object in an image and to draw bounding boxes around them is a tough problem to solve. To solve this problem, R-CNN algorithm was published in 2014. After R-CNN, many of its variants like Fast-R-CNN, Faster-R-CNN and Mask-R-CNN came which improvised the task of object detection. To understand the latest R-CNN variants, it is important to have a clear understanding of R-CNN.

A member of the generalized linear model (GLM) family and similar to linear regression in many ways, logistic regression (despite the confusing name) is used for classification problems with two possible outcomes. Logistic regression is handy for classification problems since it fits an S shaped logistic (or Sigmoid) function to the data, squishing the linear equation to an output range of 0–1. This convenient range allows logistic regression to model the probabilities of a data point belonging to a particular class, typically with the decision point at the probability of .5. So, what does that look like in math? How does the sigmoid function squish the linear equation?

With about one billion proton–proton collisions per second at the Large Hadron Collider (LHC), the LHC experiments need to sift quickly through the wealth of data to choose which collisions to analyse. To cope with an even higher number of collisions per second in the future, scientists are investigating computing methods such as machine-learning techniques. A new collaboration is now looking at how these techniques deployed on chips known as field-programmable gate arrays (FPGAs) could apply to autonomous driving, so that the fast decision-making used for particle collisions could help prevent collisions on the road. FPGAs have been used at CERN for many years and for many applications. Unlike the central processing unit of a laptop, these chips follow simple instructions and process many parallel tasks at once.

With about one billion proton–proton collisions per second at the Large Hadron Collider (LHC), the LHC experiments need to sift quickly through the wealth of data to choose which collisions to analyse. To cope with an even higher number of collisions per second in the future, scientists are investigating computing methods such as machine-learning techniques. A new collaboration is now looking at how these techniques deployed on chips known as field-programmable gate arrays (FPGAs) could apply to autonomous driving, so that the fast decision-making used for particle collisions could help prevent collisions on the road. FPGAs have been used at CERN for many years and for many applications. Unlike the central processing unit of a laptop, these chips follow simple instructions and process many parallel tasks at once.

This post is part three of a series of posts introducing the Redis-ML module. The first article in the series can be found here. The sample code for this post requires several Python libraries and a Redis instance running Redis-ML. Detailed setup instructions to run the code can be found in either part one or part two of the series. Logistic regression is another linear model for building predictive models from observed data.

Artificial intelligence is set to be the stepping stone between driver assistance systems and truly autonomous vehicles. You'd be forgiven for thinking that fully autonomous cars were just around the corner. In some respects, of course, they are. Partial automation – along the lines of Tesla's much-publicised Autopilot – is set to become commonplace on premium cars over the next few years. Even when it comes to higher levels of autonomy, much of the required hardware is already available.