**Mixture of Logistic Distributions (MoL)** is a type of output function, and an alternative to a [softmax](https://paperswithcode.com/method/softmax) layer. Discretized logistic mixture likelihood is used in [PixelCNN](https://paperswithcode.com/method/pixelcnn)++ and [WaveNet](https://paperswithcode.com/method/wavenet) to predict discrete values.

Image Credit: [Hao Gao](https://medium.com/@smallfishbigsea/an-explanation-of-discretized-logistic-mixture-likelihood-bdfe531751f0)

**Meena** is a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. A seq2seq model is used with the Evolved [Transformer](https://paperswithcode.com/method/transformer) as the main architecture. The model is trained on multi-turn conversations where the input sequence is all turns of the context and the output sequence is the response.

Meena

Towards a Human-like Open-Domain Chatbot

Mixture of Logistic Distributions

**Inception-v3** is a convolutional neural network architecture from the Inception family that makes several improvements including using [Label Smoothing](https://paperswithcode.com/method/label-smoothing), Factorized 7 x 7 convolutions, and the use of an auxiliary classifer to propagate label information lower down the network (along with the use of [batch normalization](https://paperswithcode.com/method/batch-normalization) for layers in the sidehead).

Year	2000
Data Source	CC BY-SA - https://paperswithcode.com