In this blog post, we will walk through the process of coding a simple fully connected neural network using the PyTorch framework. We will explain each step and build the basic architecture of the network. The goal of this network is to classify handwritten digits from the MNIST dataset. Let's start by importing the necessary … Continue reading Building a Simple Neural Network with PyTorch →

Gradient ClippingGradient CheckpointingGradient RollbackGradient Accumulation Gradient ClippingGradient clipping is a technique to prevent exploding gradients in very deep networks, usually in recurrent neural networks. A neural network is a learning algorithm, also called neural network or neural net, that uses a network of functions to understand and translate data input into a specific output.With gradient … Continue reading Decode some Deep Learning phrases →

In the Hugging Face community event I learned how to use FAISS(Facebook AI Similarity Search) to find documents that are most semantically similar to a given query. The goal of this project is to extend this idea to build a retrieval and reranking system, where the retriever returns possibly relevant results, while the reranker evaluates … Continue reading Create your own search engine →

Let’s say we have two Jupyter notebooks and we need to share a variable from first notebook to the second notebook. How can we do that? Jupyter provides magic commands to ease operations which are complex otherwise. The magic command we are going to use today is %store. The %store magic command saves the specified … Continue reading How to share variables between two different Jupyter notebooks ? →

Linear regression may be both the simplest and most popular among the standard tools to regression.Dating back to the dawn of the 19th century, linear regression flows from a few simpleassumptions. First, we assume that the relationship between the independent variables x and thedependent variable y is linear, i.e., that y can be expressed as … Continue reading Basic Elements of Linear Regression Model →

Affine functions is a vector-valued functions of the form f(x_1,…,x_n)=A_1x_1+…+A_nx_n+b These coefficients can be scalar or dense or sparse matrices. The constant term is a scalar or a column vector. In geometry, an affine transformation or affine map (from the Latin, affinis, "connected with") between two vector spaces consists of a linear transformation followed by … Continue reading Affine Function →

When I asked a GPT-2 transformer about "what is life", We can see how beautifully this model portray its thought about life. This is my first write up from GPT-2. Will post more such stories using these transformer models. "Life is suffering and pleasure. You are suffering for the pain you have caused yourself. Your … Continue reading Write with transformer →

Some of the most useful operators in linear algebra are norms. Informally, the norm of a vectortells us how big a vector is. The notion of size under consideration here concerns not dimensionalitybut rather the magnitude of the components. In linear algebra, a vector norm is a function f that maps a vector to a … Continue reading Vector Norm in Machine Learning →