Qualitative similarities and differences in visual object representations between brains and deep networks

Deep neural networks have revolutionized computer vision, and their object representations across layers match coarsely with visual cortical areas in the brain. However, whether these representations exhibit qualitative patterns seen in human perception or brain representations remains unresolved. Here, we recast well-known perceptual and neural phenomena in terms of distance comparisons, and ask whether they are present in feedforward deep neural networks trained for object recognition. Some phenomena were present in randomly initialized networks, such as the global advantage effect, sparseness, and relative size. Many others were present after object recognition training, such as the Thatcher effect, mirror confusion, Weber’s law, relative size, multiple object normalization and correlated sparseness. Yet other phenomena were absent in trained networks, such as 3D shape processing, surface invariance, occlusion, natural parts and the global advantage. These findings indicate sufficient conditions for the emergence of these phenomena in brains and deep networks, and offer clues to the properties that could be incorporated to improve deep networks.

The Rise of Industrial Espionage and How to Prevent It

Innovations in digital technology are progressing at an unprecedented rate, and countries and all types of actors are capitalizing on these advancements. Moreover, if first adopters can obtain the digital technology without spending the lengthy time and ample funds for research and development of it, but rather through industrial espionage, this gives countries the potential global advantage without the costs. Included are further details on the rise of industrial espionage, its key issues, and effects on the internet and network security, the applicable hacking attacks and countermeasures, and major predictions and future issues.

Manufacturing Production Companies Can Gain Strategic Global Advantage Using Lean Six Sigma

How the implementation of Lean Six Sigma in manufacturing production companies in the global environment can positively affect innovation, quality, education, productivity, standard of living, and ethics is discussed in this chapter. Examples by notables like Dr. W. Edwards Deming and the Chegg Study point out a serious misalignment between what is actually needed in manufacturing production worker skill sets and what is available. The chapter demonstrates the interconnectivity of, and responsibility for, the welfare of citizens of the world. It shows how Lean Six Sigma implementation can influence Gross National Product and Gross Domestic Product, which in turn determine quality of life for a nation's citizens. The chapter offers solutions like fostering industry, academics, and government relationships for the abatement of problems such as less government funding for public education and equipping college students with the right skill sets for more complex jobs in manufacturing production industries.

Do deep neural networks see the way we do?

ABSTRACTDeep neural networks have revolutionized computer vision, and their object representations match coarsely with the brain. As a result, it is widely believed that any fine scale differences between deep networks and brains can be fixed with increased training data or minor changes in architecture. But what if there are qualitative differences between brains and deep networks? Do deep networks even see the way we do? To answer this question, we chose a deep neural network optimized for object recognition and asked whether it exhibits well-known perceptual and neural phenomena despite not being explicitly trained to do so. To our surprise, many phenomena were present in the network, including the Thatcher effect, mirror confusion, Weber’s law, relative size, multiple object normalization and sparse coding along multiple dimensions. However, some perceptual phenomena were notably absent, including processing of 3D shape, patterns on surfaces, occlusion, natural parts and a global advantage. Our results elucidate the computational challenges of vision by showing that learning to recognize objects suffices to produce some perceptual phenomena but not others and reveal the perceptual properties that could be incorporated into deep networks to improve their performance.

How the forest interacts with the trees: Multiscale shape integration explains global and local processing

ABSTRACTHierarchical stimuli (such as a circle made of diamonds) have been widely used to study global and local processing. Two classic phenomena have been observed using these stimuli: the global advantage effect (that we identify the circle faster than the diamonds) and the incongruence effect (that we identify the circle faster when both global and local shapes are circles). Understanding them has been difficult because they occur during shape detection, where an unknown categorical judgement is made on an unknown feature representation.Here we report two essential findings. First, these phenomena are present both in a general same-different task and a visual search task, suggesting that they may be intrinsic properties of the underlying representation. Second, in both tasks, responses were explained using linear models that combined multiscale shape differences and shape distinctiveness. Thus, global and local processing can be understood as properties of a systematic underlying feature representation.

The Responsibility of States

This chapter explores the rationale for the special responsibility of nation-states to secure human rights and structural justice. It explains what makes states unique moral agents, in particular their responsibility to address structurally unjust conditions that give rise to human rights violations within their borders. However, it rejects prominent arguments for the conclusion that states have only a preventive and remedial role in the presence of domestic structural unfairness and human rights violations. The chapter defends the Principle of Interstate Reciprocity, which sets moral limits on the pursuit of national benefit, global advantage, and the exercise of power over others, and it concludes with an account of four unfair forms of control exercised by various supranational institutions, often in combination with powerful states and other non-state institutional agents.