# Softmax function

## Papers overview

Semantic Scholar uses AI to extract papers important to this topic.

Highly Cited

2018

Highly Cited

2018

- ICLR
- 2018

We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models… (More)

Is this relevant?

Highly Cited

2017

Highly Cited

2017

- ArXiv
- 2017

In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks… (More)

Is this relevant?

Highly Cited

2017

Highly Cited

2017

- ICML
- 2017

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our… (More)

Is this relevant?

2017

2017

- AAAI
- 2017

Neural network language models (NNLMs) have attracted a lot of attention recently. In this paper, we present a training method… (More)

Is this relevant?

Highly Cited

2016

Highly Cited

2016

- ArXiv
- 2016

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks… (More)

Is this relevant?

Highly Cited

2016

Highly Cited

2016

- ICML
- 2016

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural… (More)

Is this relevant?

Highly Cited

2013

Highly Cited

2013

- NIPS
- 2013

The recently introduced continuous Skip-gram model is an ef fici nt method for learning high-quality distributed vector… (More)

Is this relevant?

Highly Cited

2010

Highly Cited

2010

- HLT-NAACL
- 2010

We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of… (More)

Is this relevant?

Highly Cited

2009

Highly Cited

2009

- NIPS
- 2009

We introduce a two-layer undirected graphical model, calle d a “Replicated Softmax”, that can be used to model and automatically… (More)

Is this relevant?

Review

2007

Review

2007

Efficient Bounds for the Softmax Function and Applications to Approximate Inference in Hybrid models

- 2007

The softmax link is used in many probabilistic model dealing with both discrete and continuous data. However, efficient Bayesian… (More)

Is this relevant?