Intuitive Shorts

Search This Blog

KL Divergence

April 10, 2021

Get link
Facebook
Twitter
Pinterest
Email
Other Apps

Cross Entropy Entropy

Get link
Facebook
Twitter
Pinterest
Email
Other Apps

Comments

Stateless Vs Stateful LSTMs

In machine learning, it is generally assumed that the training samples are Independent and Identically Distributed (IID). As far as the sequence data is concerned, this isn't always true. If the sequence values have temporal dependence among them, such as Time Series data, the IID assumption fails. The sequence modelling algorithms hence come in two flavours, Stateless and Stateful, depending upon the architecture used while training. Following is a discussion using LSTM as an example, but the notion is applicable to other variants as well namely RNN, GRU etc. Stateless This architecture is used when the IID assumption holds. While creating batches for training, this means that there is no inter-relationship across the batches and each batch is independent from one another. The typical training process in a stateless LSTM architecture is shown below: The way these the two architectures differ is the manner in which the states (cell and hidden states

[Project] Speech emotion based Face generation using Conditional GAN

Links : [ Code ], [ Video ] The aim of this project is to develop and combine two standalone deep learning techniques - Speech Emotion Recognition (SER) and Conditional GAN (cGAN) to develop an end-to-end system for generating human faces using cGAN based on emotions identified from human speech using SER. The project pipeline can be summarized as follows: Project Pipeline : Emotion identified using SER is used to condition face generation by cGAN The project demo is shown below: Dataset:

MiniMax : A Game Playing Algorithm

Minimax is an algorithm in game theory to find the optimal move for a player, assuming that your opponent also plays optimally. It is widely used in two player turn-based games such as Tic-Tac-Toe, Backgammon, Mancala, Chess, etc. The data structure used to visualize the game progression is called "Game Tree" and looks like the one shown below. Each level in the game tree represents all the possible moves available to the player at that turn. The name "MiniMax" is derived from "Min" and "Max", the two participating players, who try to play the most optimum moves on their turn. "Max" on each of its turn tries to play the move that maximizes the state value function. "Min" on the other hand tends to minimize this value. Its important to note here that the game tree corresponding to a particular game is drawn beforehand. Minimax algorithm is just a way to traverse through it (in a depth first search fashion) in su

Powered by Blogger

KL Divergence

Comments

Post a Comment