Tag Archive

Blog on All Things Cloud Foundry

Introduction to Neural Networks and Meta-Frameworks for Deep Learning with TensorFlow

Roger Strukhoff

long-short-term-memory-networks-and-tensorflow

With sample code and demos, this blog post highlights major topics covered at a recent TensorFlow webinar: what it takes to train a recurrent / convolutional neural network, four unique object types, meta-frameworks, etc.

(more…)

No Comments

Using Machine Learning and TensorFlow to Recognize Traffic Signs

Sophie Turol

traffic-sign-recognition-with-tensorflow-v12

This time, TensorFlow meetup in Silicon Valley offered the attendees a practical session aimed at enabling a neural network to classify traffic signs. With machine learning, the solution can be applied to recognize signs right on the go while driving in a car.

(more…)

No Comments

The Diversity of TensorFlow: Wrappers, GPUs, Generative Adversarial Networks, etc.

Sophie Turol

deep-convolutional-generative-adversarial-networks-v2

Enjoying its popularity, TensorFlow is now used in a variety of areas (e.g., to style images or automate cucumber sorting). At the recent meetup in Paris, attendees learnt a number of TensorFlow use cases and related deep learning tools, as well as got familiar with generative adversarial networks.

(more…)

No Comments

Analyzing Text and Generating Content with Neural Networks and TensorFlow

Sophie Turol

tensorflow-meetup-denver-2016

Can convolutional neural networks, typically used for image processing, accelerate text processing? Where do word embeddings come in here to help? How to generate unique content by using TensorFlow? This blog post explores these questions as discussed at the recent TensorFlow meetup in Denver.

(more…)

No Comments

Machine Learning for Automating a Customer Service: Chatbots and Neural Networks

Sophie Turol

munich_tensorflow_meetup

How artificial intelligence and chatbots can drive the future? What are the hidden errors when training a neural network and how to cope with them? The answers to these questions were provided at the recent TensorFlow meetup in Munich.

(more…)

No Comments

What Is Behind Deep Reinforcement Learning and Transfer Learning with TensorFlow?

Sophie Turol

tensorflow-madrid-v11

At the recent TensorFlow meetup in Madrid, the speakers explored the concept of deep reinforcement learning and learnt how to train a model with little data available.

(more…)

No Comments

TensorFlow and OpenPOWER Driving Faster Cancer Recognition and Diagnosis

Roger Strukhoff

tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis-v16

At IBM Edge 2016, a team of developers and data scientists presented a practical study that evaluated the efficiency of training a TensorFlow model in a distributed mode. A use case featured high-resolution images of lymph nodes used for possible cancer detection.

Relying on a distributed model of TensorFlow and high-performing nature of the OpenPOWER infrastructure, the demonstrated system can accelerate medical data analysis—depending on the number of GPUs and nodes in its cluster. The particular subjects of the research were how training time decreases when the cluster grows and whether the accuracy of the results is affected by the distributed nature of the computations. Read this post for brief results and technical details.

(more…)

No Comments

How TensorFlow Can Detect and Predict Wildfires

Sophie Turol

tensorflow-meetup-in-washington-dc-march-2016

At the recent Tensorflow meetup in Washington DC, the attendees learnt how TensorFlow can help in automating wildfire detection/prediction, as well as what’s underlying the TensorFlow four core concepts.

(more…)

2 Comments

How TensorFlow Can Help to Perform Natural Language Processing Tasks

Sophie Turol

tensorflow-meetup-in-silicon-valley-january-2016

At the recent TensorFlow meetup in Silicon Valley, one of the speakers showed some demos that depict natural language processing tasks in action. In addition, the attendees learnt how TensorFlow can be utilized to carry out such tasks.

(more…)

No Comments

Recurrent Neural Networks: Classifying Diagnoses with Long Short-Term Memory

Sophie Turol

tensorflow_los_angeles

When training a recurrent neural network, one can face a bunch of challenges. Long short-term memory networks (LSTM) can come to a rescue, proving to be effective for learning from sequence data. These networks can be applied for modeling varying length sequences and capturing long-range dependencies.

At the recent TensorFlow meetup in Los Angeles, the attendees learnt how to use an LSTM network for modeling clinic data.

(more…)

No Comments

Next Page »

Benchmarks and Research

Subscribe to new posts

Get new posts right in your inbox!