Author: Darren Bird

With the HPC Viper team, the senior RSE has been investigating the python API Keras which vastly simplifies the programming of deep learning computational graphs. Using a number of the free-available data sets including the mnist character sets. The outcomes have been very encouraging and allow the researcher to concentrate on the neural nets interconnections rather than the depth of programming and optimisation that other libraries demand.

A typical neural net can be constructed with 9 lines of code, as below:


model = Sequential()

model.add(Convolution2D(32, 3, 3, activation='relu', input_shape=(1,28,28)))
model.add(Convolution2D(32, 3, 3, activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))


Nvidia’s GTC-Europe conference was held at Munich, Germany this year. It not only showcases the latest development in hardware development but is strongly based on the technologies of machine learning and now deep learning. The conference as always starts with a 2/3 hour keynote speech by Nvidia’s founder and CEO Jensen Huang; areas covered were:

• Where GPU fit in and the re-engagement of Moore’s law
• Growth of deep learning applications (Nobel prizes in physics and chemistry)
• Use of image classification and other GPU industries
• Nvidia’s holodeck technology
• Intelligent machines (referencing IoT)
• Autonomous Driverless cars
• Pegasus (Robo taxi drive PX)
• Project Isaac (AI robot simulator)