The following video presents What is a Neural Network – Ep. 2 (Deep Learning SIMPLIFIED):
“With plenty of machine learning tools currently available, why would you ever choose an artificial neural network over all the rest? This clip and the next could open your eyes to their awesome capabilities! You’ll get a closer look at neural nets without any of the math or code – just what they are and how they work. Soon you’ll understand why they are such a powerful tool!…
Deep Learning is primarily about neural networks, where a network is an interconnected web of nodes and edges. Neural nets were designed to perform complex tasks, such as the task of placing objects into categories based on a few attributes. This process, known as classification, is the focus of our series….“
The following video presents 3 reasons to go Deep – Ep. 3 (Deep Learning SIMPLIFIED):
“With so many alternatives available, why are neural nets used for Deep Learning? Neural nets excel at complex pattern recognition and they can be trained quickly with GPUs.
Historically, computers have only been useful for tasks that we can explain with a detailed list of instructions. As such, they tend to fail in applications where the task at hand is fuzzy, such as recognizing patterns. Neural Networks fill this gap in our computational abilities by advancing machine perception – that is, they allow computers to start to making complex judgements about environmental inputs. Most of the recent hype in the field of AI has been due to progress in the application of deep neural networks.
Neural nets tend to be too computationally expensive for data with simple patterns….. As the pattern complexity increases, neural nets start to outperform other machine learning methods. At the highest levels of pattern complexity – high-resolution images for example – neural nets with a small number of layers will require a number of nodes that grows exponentially with the number of unique patterns. Even then, the net would likely take excessive time to train, or simply would fail to produce accurate results…..
As a result, deep nets are essentially the only practical choice for highly complex patterns such as the human face. The reason is that different parts of the net can detect simpler patterns and then combine them together to detect a more complex pattern. For example, a convolutional net can detect simple features like edges, which can be combined to form facial features like the nose and eyes, which are then combined to form a face (Credit: Andrew Ng). Deep nets can do this accurately – in fact, a deep net from Google beat a human for the first time at pattern recognition.
However, the strength of deep nets is coupled with an important cost – computational power. The resources required to effectively train a deep net were prohibitive in the early years of neural networks. However, thanks to advances in high-performance GPUs of the last decade, this is no longer an issue. Complex nets that once would have taken months to train, now only take days.“
This is an update to the previous blog, Sony’s Neural Network Libraries are Available in Open Source (No Cost) for Creating Deep Learning Programs for Artificial Intelligence: Applications Include Image & Voice Recognition, Machine Translation, Signal Processing and Robotics.
Sony’s Neural Network Console is a deep learning tool for training, evaluating, and designing neural networks.
- In June 2017, Sony released its Neural Network Libraries as open source software.
- Recently, Sony released an app, Neural Network Console V1.0.0 for Windows 8.1/10_64bit, to make deep learning even more intuitive. It is hoping to spur more deep learning-related development in the industrial world by providing this newly developed console software that can use its GUI (graphical user interface) to operate the core libraries as well as design, train and evaluate neural network models.
The key highlights of Sony’s Neural Network Console include:
- Hands-on: Start using deep learning with an intuitive user interface.
- Drag and drop for trial and error: Use a rich variety of neural layers to design your cutting-edge network. A comfortable UI will help you implement new ideas instantly.
- Automatic Structure Search: Tired of fine-tuning your network by hand? Neural Network Console can automatically search for a lightweight, high-performance neural network structure for you.
- Train and examine with a click of a button: After designing a network, training the network using our Neural Network Libraries is a simple click away. View the progress and performance in real time.* The Neural Network Libraries are the core libraries of the Neural Network Console.
- Manage Your Training History: Browse your history of the neural networks you have trained. View the performance of each network at a glance.
The following video presents Introduction of Neural Network Console:
“A deep learning tool for training, evaluating, and designing neural networks. Start using deep learning with an intuitive user interface.“
PRESS RELEASE
