Project Frigatebird. Link Github Code Taking instantaneous decisions during an uncertain situation is near impossible for machines even when considering multi-level observations and their striving ability to learn complex policies. This progress is facilitated by the availability of abundant data, simulators such as games. These projects ... Read more 10 Nov 2018 - 2 minute read
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin Ming-Wei Chang Kenton Lee Kristina Toutanova Abstract What’s BERT BERT stands for Bidirectional Encoder Representations from Transformers. How BERT is unique BERT is designed to pre-train deep bidirectional representations by jointl... Read more 06 Nov 2018 - 9 minute read
Difference between Deep Networks vs Shallow Networks ? Deep Networks - The number of hidden layers are more in deep networks with large number of parameters. Since there are higher number of parameters, higher the degree of non-linearity in the network. Hence this increases the capability to extract high level features. Shallow Networks - The ... Read more 31 Oct 2018 - 2 minute read
Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network Current trend We propose a highly efficient and faster Single Image Super-Resolution (SISR) model with Deep Convolutional neural networks (Deep CNN). Deep CNN have recently shown that they have a significant reconstruction performance on single-... Read more 29 Oct 2018 - 6 minute read
One Model To Learn Them All This paper demonstrates a single model to solve problems spanning from multiple domains. This model is trained on ImageNet , COCO dataset , a speech recognition corpus, and an English parsing task. Fluid Annotation A tool for image annotation. This is a model which perfor... Read more 29 Oct 2018 - 1 minute read
Densenet-Densely Connected Convolutional Networks Paper Let’s understand Densenet. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one betw... Read more 25 Oct 2018 - 5 minute read
Pointwise Convolution or 1x1 convolution It is a 1x1 convolution kernel. This helps in acquiring pixel by pixel level feature extraction. But the main purpose is, When the number channels in the previous layers needs to be shrinked , then we use 1x1 convolution. This reduces the problem of computational cost. For all the features lear... Read more 17 Oct 2018 - 1 minute read
Link: Google AI Paper: Available here This paper from Google Brain Team was about visual question answering , visual reasoning. This paper addressess the shortcomings of Visual Question Answer(VQA) dataset with additional parametric information such as time and memory. Additionally, there is a Reasoning Agent whose task is as quoted from... Read more 13 Oct 2018 - 1 minute read
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks The receptive field size is a crucial issue in many visual tasks , as the output must respond to large enough areas in the image to capture information about large objects. The effective receptive field show that it both has Gaussian distribution and onl... Read more 29 Sep 2018 - 2 minute read