Efficient Architecture Search by Network Transformation

Understand

Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results.

• However, their success is based on vast computational resources (e.g.
• hundreds of GPUs), making them difficult to be widely used.
• A noticeable limitation is that they still design and train each network from scratch during the exploration of the architecture space, which is highly inefficient.