ReLU is one of the widely used activation functions. For any \(x > 0\), the output of ReLU is \(x\) and \(0\) otherwise. So,\ We can also write it as \(ReLU(x) = max(0, x)\). For rest of the post let’s say \(f(x) = ReLU(x)\)....
Mar 12, 2022
We are saying the present era to be the era of ‘Machine learning’. I am a learner, who is trying to learn about machine learning each and every day. I thought it would be a great idea to share what I am learning. So here I am. Hope this can help a machine learning or AI enthusiast like me.
ReLU is one of the widely used activation functions. For any \(x > 0\), the output of ReLU is \(x\) and \(0\) otherwise. So,\ We can also write it as \(ReLU(x) = max(0, x)\). For rest of the post let’s say \(f(x) = ReLU(x)\)....
Whoever is out there, working with Machine Learning models, overfitting must be a challenge for us. We can overcome this challenge by going out and collecting more data. But this can be costly, time-consuming, or sometimes even impossible for individuals! So, what do we do? We can follow some regularization techniques. Weight Decay is...
Posted on Oct 01, 2021
In almost every application related to NLP, we use text as a part of the data. To the models, the input is generally a list of words or sentences like “We will live on Mars soon”. To a model, we feed the text as a sequence of tokens. The tokens can be characters, space-separated...
Posted on Jul 16, 2021
Currently, Attention-based recurrent Encoder-Decoder models provide an elegant way of building end-to-end models for different tasks, like automatic speech recognition (ASR), machine translation (MT), etc. An end-to-end ASR model folds traditional acoustic model, pronunciation model, and language model (LM) into a single network. An encoder maps the input speech to a sequence of higher-level...
Throughout the evolution, several metrics have been introduced to evaluate the performance of a Machine Learning algorithm or model. Sometimes it can be tricky to choose the correct metric for evaluating our model. In this article I have tried to discuss some basic matrics used in ML-related tasks and when to use which metric....
Nowadays for a lot of tasks, we are using deep neural networks or deep learning. While working with deep learning very often we face situations like overfitting and overconfidence. Overfitting is relatively well studied and can be tackled with several strategies like dropout, weight regularization, early stopping, etc. We have tools for tackling overconfidence...
In machine learning, overfitting is a very commonly used term. But what is overconfidence? Let’s talk about this today with some solid background and examples. Well, if we think about overconfidence in our general life – what pops in our mind about it? It’s being excessively confident about something. Like we are driving a...
Posted on Jul 02, 2021
In this post, we are going to discuss KFold and StratifiedKFold with some real-time examples. While working with a supervised machine learning model, we have some data with features and labels or targets. During the training, we give some portion of the data and keep a portion for test the model. Thus, we need...
In the simplest words, TensorFlow Hub is a repository. Many pre-trained models are available in the repository. So, these are ready to fine-tune and deploy anywhere. It includes text embeddings, image classification models, TF.js/TFLite models, and many more....