LSTM–Digging Deep Part 1

Introduction LSTM (Long Short Term Memory) is gaining a lot of recognition in recent past. LSTM are an interesting type of deep learning network, they are used in some fairly complex problem domain such as language translation, automatic image captioning and text generation. LSTM are designed specifically for sequence prediction…
Read More

LSTM for Stock Markets

LSTM Basics got us to a point of understanding simple LSTM. When it comes real life scenarios the picture gets more complicated a simple 1 layer LSTM just doesnt do the job. Usually multi layer LSTM are required where each layer does a part of the job then sends the…
Read More

Blockchain and MDM Synergies

As the team at Vision Insight AI continue to build in the intelligent way of doing Data Management. The world around us has one harder topic to consider i.e. Blockchain. The current state of data is we are highly distributed by nature, for example banking, healthcare, transportation, energy, manufacturing, and…
Read More

Thoughts on Distributed Tensor Flow Execution

Introduction Having worked on DNN on a single machine with reasonable GPU compute can still take large network to train for days altogether. There is always the option to use TF on a cluster on cloud environment. I apparently wanted to start with distributing my workload across the GPU and…
Read More

Azure Data Share

Azure Data Share a new feature to share data between organizations. The regions are slightly limited to 3 as of now but will grow in the future. Under the hood it’s a PaaS based share service which expose selected data from Azure storage to the selected parties and has a…
Read More

AI MDM Management

Background Master Data Management has been around for over a decade now. As we enter the new age where Data has become currency, most companies tend to spend a lot of there time bringing in data from various sources or systems. Having moved in the data to a common platform…
Read More