The battle of object detection based on deep learning algorithms is moving on the edge devices with various types of devices from NVIDIA with Jetson-family [1], Google Coral Board [2]. Even though, current SOTA object algorithms can perform excellently on desktop computers with heavy GPU capacity there is still a large gap in both terms of speed and accuracy when converting and running those models on edge devices. YOLO-Ret [3] with MobileNetV2x0.75 as a backbone network operate real-time on Jetson Nano at around 48 frames-per-second (fps). The object detection algorithms are based on deep learning methods, both in single-stage as well as two-stage methods, rely on multi-scale features. One of the most popular multi-scale architecture is Feature Pyramid Networks (FPN) [4], which created a top-down path from high-level features towards low-level features in order to enhance the accuracy of detection layers using shallower features.

This course is about the fundamental concepts of machine learning, focusing on regression, SVM, decision trees and neural networks. These topics are getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. Learning algorithms can recognize patterns which can help detect cancer for example or we may construct algorithms that can have a very good guess about stock prices movement in the market. In each section we will talk about the theoretical background for all of these algorithms then we are going to implement these problems together. We will use Python with SkLearn, Keras and TensorFlow.

Welcome to KGP Talkie's Natural Language Processing (NLP) course. It is designed to give you a complete understanding of Text Processing and Mining with the use of State-of-the-Art NLP algorithms in Python. We will learn Spacy in detail and we will also explore the uses of NLP in real life. This course covers the basics of NLP to advance topics like word2vec, GloVe, Deep Learning for NLP like CNN, ANN, and LSTM. I will also show you how you can optimize your ML code by using various tools of sklean in python.

PyTorch is a Deep Learning framework for training and running Machine Learning (ML) Models, accelerating the speed from research to production. The PyTorch C API can be used to write compact, performance sensitive code with Deep Learning capabilities to perform ML inference on mobile platforms. For a general introduction on how to deploy a PyTorch model to production, please see this article. PyTorch Mobile currently supports deploying pre-trained models for inference on both Android and iOS platforms. Download and install PyTorch from source on a Linux machine.

You have a piece of paper with text on it, and you want to build a model that can translate this text to another language. How do you approach this? The first problem is the variable size of the text. There's no linear algebra model that can deal with vectors with varying dimensions. The default way of dealing with such problems is to use the bag-of-words Model ( 1).

Optimization problems involve the identification of the best possible solution among several possibilities. These problems can be encountered in real-world settings, as well as in most scientific research fields. In recent years, computer scientists have developed increasingly advanced computational methods for solving optimization problems. Some of the most promising techniques developed so far are based on artificial neural networks (ANNs). Researchers at the Vector Institute, University of Waterloo and Perimeter Institute for Theoretical Physics in Canada have recently developed variational neural annealing, a new optimization method that merges recurrent neural networks (RNNs) with the principle of annealing.

Large Batch Size had till recently been viewed as a deterrent for good accuracy. However recent studies show that increasing the batch size can significantly reduce the training time while maintaining a considerable level of accuracy. In this blog, we draw on our inferences from four such technical papers. The RMSprop Warm-up phase is used to address the optimization difficulty at the start of the training. The update rule demonstrated below utilizes both the Stochastic Gradient Descent (SGD) along the RMSprop optimization algorithm.

Deep learning has seen a lot of recent success in tackling difficult problems that require extracting useful information from large amounts of data. Such work has shown promising results for learning difficult tasks in image recognition, natural language, time-series forecasting, etc. Traditionally, these networks have millions of parameters that are learned using an optimization algorithm. Optimization informs parameters how to update to capture features of the input relevant for learning the task at hand. While these models are often well suited for the tasks on which they are applied, they have not yet shown the ability to bootstrap a-priori knowledge for novel tasks. Even the limited approaches that show some transfer of previously learned knowledge don't scale, in terms of resources, in the same manner as seen in biological brains.

This course is about the fundamental concepts of machine learning, focusing on regression, SVM, decision trees and neural networks. These topics are getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. Learning algorithms can recognize patterns which can help detect cancer for example or we may construct algorithms that can have a very good guess about stock prices movement in the market. In each section we will talk about the theoretical background for all of these algorithms then we are going to implement these problems together. We will use Python with SkLearn, Keras and TensorFlow.

Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments show that our method is model-agnostic and can significantly improve the performance, the generalizability, and the training efficiency of current state-of-the-art navigation agents without increasing model complexity.