DSpace@MIT

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 ...

Visually-grounded spoken language datasets can enable models to learn cross-modal correspon- dences with very weak supervision. However, modern audio-visual datasets contain biases that un- dermine the real-world performance ...

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 ...

Various artificial neural networks developed by engineers have been evaluated as models of the brain, such as the ventral stream in the primate visual cortex. After being trained on large datasets, the network outputs are ...

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 ...

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 ...

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 ...

In [42] we suggested that any memory stored in the human/animal brain is forgotten following the Ebingghaus curve – in this follow-on paper, we define a novel algebraic structure, a Forgetting Neural Network, as a simple ...

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 ...

Transformer-based models achieve great performance on Visual Question Answering (VQA). How- ever, when we evaluate them on systematic generalization, i.e., handling novel combinations of known concepts, their performance ...