Transformer is a seq2seq model proposed by 8 Google employees in 2017 and initially applied to neural machine translation. But before transformer, let’s discuss what were used for the seq2seq task and their cons. Recurrent Neural Network(RNN) Given a sequences X_n it produces sequence of Y_n. In t time step, it takes the given input and previous hidden state as input to produce ouput and hidden state which act as input for t+1....
Model Optimization Most deep learning models are made up of millions/billions of parameters. So, when we inference a model, we need to load all its parameter in the memory, this means big models cannot be loaded easily on a edge/embedded devices. So, this blog is focused on optimizing a model through different techniques and analyze its effect on inference time, model size, accuracy. Model optimization is transforming machine/deep learning model such that it has:...
Artificial Intelligence: The Future is Now Introduction Artificial Intelligence (AI) is a revolutionary technology that aims to create intelligent machines capable of performing tasks that typically require human intelligence. It encompasses various subfields like machine learning, natural language processing, computer vision, and more. As AI continues to advance rapidly, its impact on industries and society as a whole is becoming increasingly profound. The Evolution of AI In the past, AI was merely a concept found in science fiction novels and movies....