Visually probe the behavior of trained machine learning models, with minimal coding.
We gather data, preprocess it, choose a model, train the model and evaluate the predictions; that’s a basic Machine Learning pipeline. Based on the results, we retrain the models for improvement, and hence, it’s an iterative process. The evaluation of models is highly dependent on the data we have. In the case of limited data, we are unable to evaluate the model across a wide range of inputs. But how great would it be if we could test our system in hypothetical situations without having to write too…
We have seen multiple breakthroughs in Natural Language Processing and Computer Vision in the domain of Artificial Intelligence. And we have seen these being applied to many applications to solve language and image-based problems. A common problem crucial to businesses around the globe is Forecasting. This can range from forecasting sales to forecasting footfall. …
There are a lot of huge datasets available on the internet for building machine learning models. But often times, we come across a situation where we have less data. With a small dataset, it becomes very easy to overfit in trying to achieve good accuracy. We end up with a model which would not then generalize well to the unseen data. If you have come across such situations, then this post is for you!
The best approach is to get more data to get a good accuracy without overfitting your model. But it’s understandable that getting more data is not…
Ever heard of Natural Langauge Processing? Whether your answer to this is a Yes or a No, this blogpost is for you!
NLP,Natural Language Processing, is a growing field in Artificial Intelligence, something that holds a lot of value in the Tech World. But even after years of work, getting results close to human level performance has been a challenge. With this field being one of the subjects for the center of attention in Deep Learning nowadays, it opens up great opportunity for researchers and developers at all levels to dive into it.
In this blogpost we’ll cover the following…
Google Colab is a great place for practising Machine learning and Kaggle is one of the best places for fetching a dataset. We’ll see in this blog post how we can easily:
So let’s begin!
Install the Kaggle library
! pip install kaggle
Create a .kaggle directory
This follows from my previous blog post here about AI consciousness, I suggest you give it a read for better understanding.
Here’s a little recap of what we discussed earlier in the previous post:
The initial layers of a CNN learn simpler features like edges, simple textures etc. The deeper layers learn more complex structures such as eyes, trees, faces, cars etc. Let’s look at an example. We’ll a pass a face image through a CNN that detects faces and we’ll look at activations in different layers of the network. Here’s our input image:
We have all heard the terms neural networks, object detection and deep learning. And we see these networks transforming science and engineering magically. We have applications like face detection, object detection, self-driving cars etc. And these are all some amazing applications of deep learning. But why do these networks work the way they work? (Read till the very end to find out!)
In this blog post we’ll dive a bit deeper into the “AI consciousness”, to get some intuition behind how these networks work and what do they see. …
TensorFlow, developed by Google, is a powerful machine learning framework. In this blog, I intend to give a basic overview of tensorflow that would help you to get yourself started with machine learning using this framework. We’ll look at some functions commonly used in tensorflow to develop a better understanding of how things work individually.
Let’s start with the tradition of “Hello world”. First we’ll import the library:
Tuning my hyper-parameters everyday to dive deeper into the foray of deep learning.