Remarkable recent success of deep neural networks has not been easy to analyze theoretically. It has been particularly hard to disentangle relative significance of architecture and optimization in achieving accurate classification on large datasets. On the flip side, shallow methods (such as kernel methods) have encountered obstacles in scaling to large data, despite excellent performance on smaller datasets, and extensive theoretical analysis. Practical methods, such as variants of gradient descent used so successfully in deep learning, seem to perform below par when applied to kernel methods. This difficulty has sometimes been attributed to the limitations of shallow architecture. In this paper we identify a basic limitation in gradient descent-based optimization methods when used in conjunctions with smooth kernels.

This paper looks at analyzing the problem of long times required for convergence of kernel methods when optimized via gradient descent. They define a notion of computational reach of gradient descent after t iterations and the failure of gradient descent to reach the epsilon neighborhood of an optimum after t iterations. They give examples of simplistic function settings with binary labels where gradient descent takes a long time to converge to the optimum. They also point out that adding regularization improves the condition number of the eigenspectrum (resulting in possible better convergence) but also leads to overregularization at times. They introduce the notion of EigenPro, where they pre-multiply the data using a preconditioner matrix, which can be pre-computed, improves the time for convergence by making the lower eigenvalues closer to the largest one as well as making cost per iteration efficient.

Timescales of neural activity are diverse across and within brain areas, and experimental observations suggest that neural timescales reflect information in dynamic environments. However, these observations do not specify how neural timescales are shaped, nor whether particular timescales are necessary for neural computations and brain function. Here, we take a complementary perspective and synthesize three directions where computational methods can distill the broad set of empirical observations into quantitative and testable theories: We review (i) how data analysis methods allow us to capture different timescales of neural dynamics across different recording modalities, (ii) how computational models provide a mechanistic explanation for the emergence of diverse timescales, and (iii) how task-optimized models in machine learning uncover the functional relevance of neural timescales. This integrative computational approach, combined with empirical findings, would provide a more holistic understanding of how neural timescales capture the relationship between brain structure, dynamics, and behavior.

Although connectionist models have provided insights into the nature of perception and motor control, connectionist accounts of higher cognition seldom go beyond an implementation of traditional symbol-processing theories. We describe a connectionist constraint satisfaction model of how people solve anagram problems. The model exploits statistics of English orthography, but also addresses the interplay of sub symbolic and symbolic computation by a mechanism that extracts approximate symbolic representations (partial orderings of letters) from sub symbolic structures and injects the extracted representation back into the model to assist in the solution of the anagram. We show the computational benefit of this extraction-injection process and discuss its relationship to conscious mental processes and working memory. We also account for experimental data concerning the difficulty of anagram solution based on the orthographic structure of the anagram string and the target word.

Thanks to the great progress of machine learning in the last years, several Artificial Intelligence (AI) techniques have been increasingly moving from the controlled research laboratory settings to our everyday life. AI is clearly supportive in many decision-making scenarios, but when it comes to sensitive areas such as health care, hiring policies, education, banking or justice, with major impact on individuals and society, it becomes crucial to establish guidelines on how to design, develop, deploy and monitor this technology. Indeed the decision rules elaborated by machine learning models are data-driven and there are multiple ways in which discriminatory biases can seep into data. Algorithms trained on those data incur the risk of amplifying prejudices and societal stereotypes by over associating protected attributes such as gender, ethnicity or disabilities with the prediction task. Starting from the extensive experience of the National Metrology Institute on measurement standards and certification roadmaps, and of Politecnico di Torino on machine learning as well as methods for domain bias evaluation and mastering, we propose a first joint effort to define the operational steps needed for AI fairness certification. Specifically we will overview the criteria that should be met by an AI system before coming into official service and the conformity assessment procedures useful to monitor its functioning for fair decisions.

In recent times there has been a lot of interest in embedding deep learning models into hardware. Energy is of paramount importance when it comes to deep learning model deployment especially at the edge. There is a great blog post on why energy matters for [email protected] by Pete Warden on "Why the future of Machine Learning is Tiny". Energy optimizations for programs (or models) can only be done with a good understanding of the underlying computations. Over the last few years of working with deep learning folks -- hardware architects, micro-kernel coders, model developers, platform programmers, and interviewees (especially interviewees) I have discovered that people understand LSTMs from a qualitative perspective but not well from a quantitative position.

Remarkable recent success of deep neural networks has not been easy to analyze theoretically. It has been particularly hard to disentangle relative significance of architecture and optimization in achieving accurate classification on large datasets. On the flip side, shallow methods (such as kernel methods) have encountered obstacles in scaling to large data, despite excellent performance on smaller datasets, and extensive theoretical analysis. Practical methods, such as variants of gradient descent used so successfully in deep learning, seem to perform below par when applied to kernel methods. This difficulty has sometimes been attributed to the limitations of shallow architecture.

Hypothesis Formation and Qualitative Reasoning in Molecular Biology

The 1988 Workshop on Cognitive Models of Speech Processing was held at Park Hotel Fiorelle, Sperlonga, Italy, on 16-20 May 1988. Twenty-five participants gathered in this small coastal village, where the Emperor Tiberius once kept a summer house, to discuss psycholinguistic and computational issues in speech and natural language processing.