Huawei Announces Kirin 970: AI In Your Phone

China’s biggest domestic mobile phone maker, Huawei, is now powering its phones with artificial intelligence (AI) engines. The Chinese tech giant today unveiled Kirin 970 — a SoC (system on a chip) for mobile phones — at IFA (Internationale Funkausstellung Berlin), one of the oldest industrial exhibitions in Germany. The chipset is powered by HiAI, […]

Continue reading


Memory, Attention, Sequences

In recent years, machine intelligence has made significant progress, thanks to the rise of deep learning. Various neural network paradigms have become state-of-the-art methods across multiple fields, such as computer vision and natural language processing etc. For specific tasks, they can even surpass human-level performance, which is a striking success. In the article “Memory, attention, […]

Continue reading


[Kaggle] SMS Spam Collection

I’ve just made some exploration on a dataset provided by Kaggle for SMS Spams Detection. I’ve managed to get a loss of 0.1 on the testing set and approx. accuracy of 95%. You can check my exploration and classification source code on the Python Notebook https://github.com/AhmedHani/Kaggle-Machine-Learning-Competitions/blob/master/Dataset%20Exploration/SMS%20Spam%20Collection%20Dataset/sms_spam_detection.ipynb Advertisements

Continue reading


Feedback Sequence-to-Sequence Model – Gonna Reverse Them All!

This tutorial assumes that you have a pretty good understanding about the basics of Recursive Neural Networks and Backpropagation Through Time (BPTT) and how these models actually work Terminologies One-to-one: Problems that are concerned into getting a direct relation between an input word and output word. For example, the relation (like, love) is considered to […]

Continue reading


Visual Attribute Transfer through Deep Image Analogy

1. Introduction Have you ever thought of swapping faces with one of your favorite movie characters? Researchers from Microsoft Research Asia and Shanghai Jiaotong University have recently published a paper on transferring visual attributes of images using a new technique called Deep Image Analogy. To demonstrate their technique, they swapped faces between Mona Lisa and […]

Continue reading


Cool IJCNN Stuff from Alaska

From May 14 to 18, the 30th International Joint Conference on Neural Networks (IJCNN 2017) was held in Anchorage, AK, USA. Continuing the long tradition, the conference is organized by the International Neural Network Society (INNS), in cooperation with the IEEE Computational Intelligence Society (IEEE-CIS). This year, there were 621 papers accepted out of 933 […]

Continue reading


Big Picture Machine Learning: Classifying Text with Neural Networks and TensorFlow

In this article, the author discusses the main six topics about creating a machine learning model to classify texts into categories: 1. How TensorFlow works 2. What is a machine learning model 3. What is a Neural Network 4. How the Neural Network learns 5. How to manipulate data and pass it to the Neural […]

Continue reading


Deep learning

Deep learning (deep machine learning, or deep structured learning, or hierarchical learning, or sometimes DL) is a branch ofmachine learning based on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers with complex structures or otherwise, composed of multiple non-linear transformations.[1][2][3][4][5] Deep learning is part of a […]

Continue reading


Large-Scale Evolution of Image Classifiers

Paper source: https://arxiv.org/pdf/1703.01041.pdf Neural networks have been proven effective at solving difficult problems but designing their architectures is sort of challenging, even only for image classification problems. Evolutionary algorithms provided a technique to discover such networks automatically. Despite significant computational requirements, it is shown that evolving models that rival large, hand-designed architectures are possible today. We […]

Continue reading


Artificial Intelligence is the New Electricity — Andrew Ng

Abstract On Wednesday, January 25, Andrew Ng – former Baidu Chief Scientist, Coursera co-founder, and Stanford Adjunct Professor – gave a talk at the Stanford MSx Future Forum. During the talk, Professor Ng shared his opinion on AI. He mainly discussed how artificial intelligence (AI) is transforming industry and business. Figure 1: Andrew Ng while […]

Continue reading