Backpropagation, which uses the chain rule, is the de-facto standard
alg...
Generalization bounds which assess the difference between the true risk ...
Contemporary predictive models are hard to interpret as their deep nets
...
A key concern in integrating machine learning models in medicine is the
...
Discrete variational auto-encoders (VAEs) are able to represent semantic...
The success of deep neural nets heavily relies on their ability to encod...
To perform counterfactual reasoning in Structural Causal Models (SCMs), ...
We present a method for matching a text sentence from a given corpus to ...
The cross entropy loss is widely used due to its effectiveness and solid...
This work focuses on object goal visual navigation, aiming at finding th...
This paper proposes an attack-independent (non-adversarial training)
tec...
Many recent datasets contain a variety of different data modalities, for...
As modern neural networks have grown to billions of parameters, meeting ...
Direct loss minimization is a popular approach for learning predictors o...
A hallmark of intelligence is the ability to deduce general principles f...
Generalization bounds which assess the difference between the true risk ...
We regard explanations as a blending of the input sample and the model's...
Direct optimization is an appealing approach to differentiating through
...
Dialog is an effective way to exchange information, but subtle details a...
The recently proposed audio-visual scene-aware dialog task paves the way...
Reparameterization of variational auto-encoders with continuous latent s...
The quest for algorithms that enable cognitive abilities is an important...
We present a co-segmentation technique for space-time co-located image
c...
We study an online learning framework introduced by Mannor and Shamir (2...
This paper presents a new approach, called perturb-max, for high-dimensi...
We present a probabilistic graphical model formulation for the graph
clu...
Contemporary deep neural networks exhibit impressive results on practica...
In this paper we present a new approach for tightening upper bounds on t...
In this paper we propose a unified framework for structured prediction w...
In this paper we relate the partition function to the max-statistics of
...