Achieving optimal throughput and latency with model inference on high client-server traffic — In real-time AI model deployment en masse, efficiency of model inference and hardware/GPU usage is paramount. The speed of a single client-server inference request depends on the Latency and Throughput of the server. This is because deep learning models are typically mounted on a server or a cluster of servers…

All about setting up, quantization and running inference with TensorRT in Linux environment — During real-time AI model deployment, speed of model prediction (or inference) is paramount. To ensure seamless user experience, the speech engine by Apple’s Siri cannot take forever to decipher a speaker’s intent and produce an appropriate response. Neither can its FaceID lag when unlocking the iPhone. Fortunately, it is possible…

A complete guide from CNN to Transfer Learning for Kaggle’s Cat versus Dog dataset — In the modern era, Neural Networks triumph over traditional Machine Learning algorithms when modelling complex data sets, especially unstructured data — spatial data (Computer Vision) or sequential data (NLP and Time Series). While leading Neural Network architectures for NLP are helmed by Transformers (since 2017, with the paper “Attention Is…

Developing deep neural networks from scratch with Mathematics and Python — Unlike traditional machine learning frameworks, deep neural networks are extremely powerful because it can capture highly non-linear relations between the features and target. And the degree of non-linearity is usually controlled by adjusting the depth of the neural network, or the number of Hidden Layers it contains. But how should…

Creating shallow neural networks from scratch with Mathematics and Python — In the previous article, we have described that the vanilla neural networks are basically Multi-Layer Perceptron (MLP), or the regular feedforward networks. Other neural network architectures, such as CNN and RNN, are more complex customization of the structure behind Perceptron layers, but forward propagation and backpropagation process similar to MLP…

Single-layer neural network with logistic regression from the bare fundamentals — Neural networks, in recent years, have been driving several artificial intelligence breakthroughs in areas in Computer Vision, Natural Language Processing, Reinforcement Learning etc. Unlike traditional machine learning, which typically works with tabular data, deep learning with neural networks may employ complex and customized architectures when working with unstructured data.

An inspired guide on how Bodhichitta can be a force for good and happiness — Martin Luther King once said, “Cowardice asks the question, “Is it safe?” Expediency asks the question, “Is it politic?” Vanity asks the question, “Is it popular?” But, conscience asks the question, “Is it right?”” What then, would compassion ask? Often, in self-help and spiritual growth literature, we hear about the…

A simple case study of Hidden Markov Model on Named Entity Recognition — In this tutorial, we will introduce and apply the Hidden Markov Model (HMM) on a simple Named Entity Recognition (NER) problem, namely the boundary segmentation of named entities in text. The Hidden Markov Model is a probabilistic model, usually applied in simple sequential machine learning problems. As the word ‘hidden’…

A short tutorial on how to blur out faces effectively for personal de-identification — Personal identity masking techniques have been applied in both Computer Vision and Natural Language Processing. Here, in Computer Vision, facial masking or personal de-identification is commonly deployed in images, videos and live-stream, when other information in these media takes greater precedence over the identity of the individuals involved.