Browsing Publications by Title
Now showing items 99118 of 124

Spatial IQ Test for AI
(20171231)We introduce SITD (Spatial IQ Test Dataset), a dataset used to evaluate the capabilities of computational models for pattern recognition and visual reasoning. SITD is a generator of images in the style of the Raven Progressive ... 
Spatiotemporal interpretation features in the recognition of dynamic images
(Center for Brains, Minds and Machines (CBMM), 20181121)Objects and their parts can be visually recognized and localized from purely spatial information in static images and also from purely temporal information as in the perception of biological motion. Cortical regions have ... 
Stable Foundations for Learning: a foundational framework for learning theory in both the classical and modern regime.
(Center for Brains, Minds and Machines (CBMM), 20200325)We consider here the class of supervised learning algorithms known as Empirical Risk Minimization (ERM). The classical theory by Vapnik and others characterize universal consistency of ERM in the classical regime in which ... 
Streaming Normalization: Towards Simpler and More Biologicallyplausible Normalizations for Online and Recurrent Learning
(Center for Brains, Minds and Machines (CBMM), arXiv, 20161019)We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and ... 
Symmetry Regularization
(Center for Brains, Minds and Machines (CBMM), 20170526)The properties of a representation, such as smoothness, adaptability, generality, equivari ance/invariance, depend on restrictions imposed during learning. In this paper, we propose using data symmetries, in the sense of ... 
Technical Report: Building a Neural Ensemble Decoder by Extracting Features Shared Across Multiple Populations
(20190905)To understand whether and how a certain population of neurons represent behavioralrelevant vari ables, building a neural ensemble decoder has been used to extract information from the recorded activity. Among different ... 
Theoretical Issues in Deep Networks
(Center for Brains, Minds and Machines (CBMM), 20190817)While deep learning is successful in a number of applications, it is not yet well understood theoretically. A theoretical characterization of deep learning should answer questions about their approximation power, the ... 
Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?
(Center for Brains, Minds and Machines (CBMM), arXiv, 20161123)[formerly titled "Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review"] The paper reviews and extends an emerging body of theoretical results on deep learning including the ... 
Theory II: Landscape of the Empirical Risk in Deep Learning
(Center for Brains, Minds and Machines (CBMM), arXiv, 20170330)Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least for the most successful Deep ... 
Theory IIIb: Generalization in Deep Networks
(Center for Brains, Minds and Machines (CBMM), arXiv.org, 20180629)The general features of the optimization problem for the case of overparametrized nonlinear networks have been clear for a while: SGD selects with high probability global minima vs local minima. In the overparametrized ... 
Theory of Deep Learning IIb: Optimization Properties of SGD
(Center for Brains, Minds and Machines (CBMM), 20171227)In Theory IIb we characterize with a mix of theory and experiments the optimization of deep convolutional networks by Stochastic Gradient Descent. The main new result in this paper is theoretical and experimental evidence ... 
Theory of Deep Learning III: explaining the nonoverfitting puzzle
(arXiv, 20171230)THIS MEMO IS REPLACED BY CBMM MEMO 90 A main puzzle of deep networks revolves around the absence of overfitting despite overparametrization and despite the large capacity demonstrated by zero training error on randomly ... 
Theory of Intelligence with Forgetting: Mathematical Theorems Explaining Human Universal Forgetting using “Forgetting Neural Networks”
(Center for Brains, Minds and Machines (CBMM), 20171205)In [42] we suggested that any memory stored in the human/animal brain is forgotten following the Ebingghaus curve – in this followon paper, we define a novel algebraic structure, a Forgetting Neural Network, as a simple ... 
Towards a Programmer’s Apprentice (Again)
(Center for Brains, Minds and Machines (CBMM), 20150403)Programmers are loathe to interrupt their workflow to document their design rationale, leading to frequent errors when software is modified—often much later and by different programmers. A Pro grammer’s Assistant could ... 
Universal Dependencies for Learner English
(Center for Brains, Minds and Machines (CBMM), arXiv, 20160801)We introduce the Treebank of Learner English (TLE), the first publicly available syntactic treebank for English as a Second Language (ESL). The TLE provides manually annotated POS tags and Universal Dependency (UD) trees ... 
Universal Format Conversions
(20200605)Information is the fuel for intelligence. Any competitive intelligence system should be information hungry. “Formats” on the other hand, is the container for information. Accessing information without the ability to decipher ... 
Universal Metaphysics
(20191231)The development of natural science especially physics allows us to understand to a large extent the material world. However, the world also contains a large amount of concepts that are nonmaterial and abstract, which are ... 
Unsupervised learning of clutterresistant visual representations from natural videos
(Center for Brains, Minds and Machines (CBMM), arXiv, 20150427)Populations of neurons in inferotemporal cortex (IT) maintain an explicit code for object identity that also tolerates transformations of object appearance e.g., position, scale, viewing angle [1, 2, 3]. Though the learning ... 
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?
(Center for Brains, Minds and Machines (CBMM), arXiv, 20140312)The present phase of Machine Learning is characterized by supervised learning algorithms relying on large sets of labeled examples (n → ∞). The next phase is likely to focus on algorithms capable of learning from very few ... 
UNSUPERVISED LEARNING OF VISUAL STRUCTURE USING PREDICTIVE GENERATIVE NETWORKS
(Center for Brains, Minds and Machines (CBMM), arXiv, 20151215)The ability to predict future states of the environment is a central pillar of intelligence. At its core, effective prediction requires an internal model of the world and an understanding of the rules by which the world ...