Machine Learning (ML)

Filtering spam using Naive Bayes

Naive Bayes is a Bayes Theorem-based probabilistic algorithm used in data analytics for email spam filtering. In this article, we have explored the step to filter spam using Naive Bayes in depth.

Disadvantages of GANs || Am I real or a Trained Model to write?

We have explored the problems with GANs in this article and have divided them into two major parts: General Problems with GANs and Technical Disadvantages of GANs.

Machine Learning (ML)

Elastic Net Regularization

Elastic Net Regularization is a regularization technique that uses both L1 and L2 regularizations to produce most optimized output. This is one of the best regularization technique.

Machine Learning (ML)

BERT and SEARCH: How BERT is used to improve searching?

In this article, we have explored how BERT model can be used to improve search results in search engines like Google Search, Bing and others.

Machine Learning (ML)

Introduction to Multilingual BERT (M-BERT)

We explored what is Multilingual BERT (M-BERT) and see a general introduction of this NLP model.

Machine Learning (ML)

Heaps' law in NLP for Frequency of Words

Heap's Law in NLP is a relation between the number of unique words to the total number of words in a document. It is, also, known as Herdan's law.

Machine Learning (ML)

Concrete Problems in AI Safety

In this article we shall explore a research paper titled “Concrete Problems in AI Safety” by Dario Amodei and others. This has been a very influential paper.

Machine Learning (ML)

Zipf's Law in NLP

According to Zipf's law, the frequency of a given word is dependent on the inverse of it's rank . Zipf's law is one of the many important laws that plays a significant part in natural language processing.

Machine Learning (ML)

Alternatives to CNN (Convolutional Neural Network)

We have explored Alternatives to CNN (Convolutional Neural Network) which includes Graph Neural Network and Capsule Neural Network.

Machine Learning (ML)

Adversarial Sample Transferability in Machine Learning: Attacks

We have discussed about what adversarial machine learning is and what transferability attacks are. The ideas are from Ian Goodfellow.

Machine Learning (ML)

Can Machine Learning (ML) be secure?

We answer the question "Can Machine Learning (ML) or Artificial Intelligence (AI) be secure?". We explore different types of attacks on Machine learning, defense strategies and more

Machine Learning (ML)

Application of BERT : Sentence semantic similarity

In this article, we have introduced another application of BERT for finding out whether a particular pair of sentences have the similar meaning or not.

Machine Learning (ML)

Application of BERT : Binary Text Classification

This article focused on implementation of one of the most widely used NLP Task "Binary Text classification " using BERT Language model and Pytorch framework.

Machine Learning (ML)

MobileNet V1 Architecture

MobileNet is an efficient and portable CNN architecture that is used in real world applications. We have explored the MobileNet V1 architecture in depth.

Machine Learning (ML)

Summary: The Case for Learned Index Structures

This outlines and evaluates the potential of a new approach to build indexes that is the merge of Algorithms/ Data Structures and Machine Learning.

Machine Learning (ML)

Adversarial Examples are not Bugs but are Features of AI

Adversarial Vulnerability is a direct result of our models' sensitivity to well-generalizing features in the data. We explored the research paper.

Machine Learning (ML)

The Indirect Convolution Algorithm

Indirect Convolution is as efficient as the GEMM primitive without the overhead of im2col transformations - instead of reshuffling the data, an indirection buffer is introduced.

Machine Learning (ML)

Summary: Learning to See by Moving

Research question: Is it also possible to learn useful features for a diverse set of visual tasks using any other form of supervision?

Machine Learning (ML)

Wiener filter

Wiener filter performs two main functions - it inverts the blur of the image and removes extra noise. It is particularly helpful when processing images that have been through a degradation filter.

Machine Learning (ML)

Summary: High Performance Convolutional Neural Networks for Document Processing

We have explored the paper "High Performance Convolutional Neural Networks for Document Processing" by Microsoft Research. It explores techniques to compute convolution layer in CNN faster.

Machine Learning (ML)

Understanding Deep Image Representations by Inverting Them

We have explore the problem that given an encoding of an image, to which extent is it possible to reconstruct the image itself? We have explored the paper "Understanding Deep Image Representations by Inverting Them".

Machine Learning (ML)

Overview of Semantic Segmentation

Semantic Segmentation is the process of labeling pixels present in an image into a specific class label. It is considered to be a classification process which classifies each pixel. The process of predicting each pixel in the class is known as dense prediction.

Machine Learning (ML)

Multinomial/ Multimodal Naive Bayes

Multimodal naive bayes is a specialized version of naive bayes designed to handle text documents using word counts as it's underlying method of calculating probability.

Machine Learning (ML)

Byte Pair Encoding for Natural Language Processing (NLP)

Byte Pair Encoding is originally a compression algorithm that was adapted for NLP usage. Byte Pair Encoding comes in handy for handling the vocabulary issue through a bottom-up process.

Machine Learning (ML)

Transformer Networks: How They Can Replace GANs

After an introduction to how transformers work, and a brief look at how they process text data, we see how they can also generate images and audio data just like GANs.