AI Activated

Originally Written on:-  11th May, 2019. Natural Language Processing There are a few concepts that are absolutely essential for NLP. Only a few has been discussed in this blog post This blog consists of a few parts:- stemming and lemmatization TF-IDF in NLP Cosine Similarity. Stemming Stemming algorithms work by cutting off the end or the beginning of the word, taking into account a list of common prefixes and suffixes that can be found in an inflected word. This indiscriminate cutting can be successful in some occasions, but not always, and that is why we affirm that this approach presents some limitations. Below we illustrate the method with examples in both English and Spanish. Stemming refers to a crude heuristic process that chops off the end of words in the hope of achieving this goal correctly most of the time and often includes the removal of derivational affixes. Overstemming and Understemming However, because ...

Originally Written on:- November,2018. Cross entropy Let us start with cross entropy and try to understand  what it is and how it works?   Cross - entropy  is commonly used to quantify the difference between two probability distributions. Now, when we develop a model for probabilistic classification, we aim to map the model's inputs to probabilistic  predictions , and we often  train  our model by incrementally adjusting the model's parameters so that our predictions get closer and closer to  ground-truth probabilities. For example, if we're interested in determining whether an image is best described as a landscape  or  as a house  or  as something else, then our model might accept an image as input and produce three numbers as output, each representing the probability of a single class. During training, we might put in an image of a landscape, and we hope that our model produces predictions that are close ...

Originally Written on:-  5th January, 2019. OpenAI taxi v2. img source: Google Images Introduction Reinforcement Learning Reinforcement Learning is the science of making optimal decisions using experiences. Breaking it down, the process of Reinforcement Learning involves these simple steps: 1.       Observation of the environment 2.       Deciding how to act using some strategy 3.       Acting accordingly 4.       Receiving a reward or penalty 5.       Learning from the past experiences and refining the strategy 6.       Iterate until an optimal strategy is found Let's now understand Reinforcement Learning by actually developing an agent to learn to play a game automatically on its own.               ...