Reinforcement Learning broadly involves Value-based methods and Policy-based Methods. Actor-based methods are suitable for discrete action spaces, whereas Policy-based methods are suitable for continuous action spaces.

A simple Policy Gradient algorithm (a policy-based method) predicts the probability of Actions of an Agent. Since, the Policy is updated using Monte Carlo approach (i.e. taking random samples), the variance of log probabilities produced by the PG algorithm is very high, causing unstable learning. This variance can be reduced by using a Baseline to remove outliers. A good choice to be used as a baseline is the Q-Value of the State, Action pair.

In this session, we will talk about Actor Critic algorithms, which uses two networks - an Actor and a Critic. The actor outputs the Policy, while the Critic gives out the Q-value which can be used to evaluate the Policy. In this zero-sum game, an equilibrium is reached when an ideal policy is discovered.

We will demonstrate with a Code demo, how this algorithm can be used to predict Actions in a Stock market scenario.

I will discuss how I started CellStrat AI Lab and what goes to make it successful as one of the leading AI research groups in India.

I will cover facets such as origination, growth, researcher motivation, content portfolio, project activity, research areas, marketing techniques and talent development pipeline.

This presentation will give an idea to corporate and academic institutions as to how they can create and nurture a world-class AI Lab within their organizations.

There has been much research in efficient and scalable model approaches required for network design and object detection. Feature Pyramid Networks (FPN) enabled feature fusion at different scales. Path Aggregation Networks (PANet) conduct bottom-up path augmentation in an FPN, which shortens information transfer from bottom layers to topmost features. A more recent scheme, NAS-FPN (Neural Architecture Search-Feature Pyramid Network), combines RL-based NAS with an FPN to enable combination of top-down and bottom-up connections to fuse features across scales.

A recent state-of-the art model EfficientDet uses a weighted bi-directional BiFPN with multi-scale feature fusion across layers to account for learnable feature importance while applying bottom-up and top-down feature fusion. EfficientDet combines BiFPN with efficient model scaling techniques proposed in EfficientNet model, such that the baseline network, the feature network and the bounding box/class prediction networks are all scaled uniformly and efficiently using compound scaling technique across resolution/width/depth dimensions. The EfficientNet-D6 achieves top of the line accuracy (mAP) on COCO dataset with 4x lesser parameters and 13x fewer FLOPS then the recent comparable NAS-FPN model.

We will train the audience how to develop advanced image segmentation with FCN/DeepLab algorithms which can help visualize the driving scenarios accurately, so as to allow the autonomous driving system to take appropriate action considering the obstacle views.

In this session, data scientists from CellStrat AI Lab will present demos and presentations on cutting-edge AI solutions in :-

• Computer Vision - Image Segmentation with FCN/UNets/DeepLab/ESPNet, Image Processing, Pose Estimation with DensePose
• Natural Language Processing (NLP) - Latest NLP and Text Analytics with BERT, NER, Neural Language Translation etc to solve problems such as text summarization, QnA systems, video captioning etc.
• Reinforcement Learning (RL) - Train Atari Video Games with RL, Augmented Random Search, Deep Q Learning etc. Apply RL techniques for gaming, financial portfolios, driverless cars etc. Train Robots with MuJoCo simulator.
• Driverless Cars - Demo on multi-class roads datasets, path planning and navigation control for cars etc.
• Neural Network Architectures - Faster and Smaller Neural Networks with MorphNet

This session will discuss Reinforcement Learning (RL) algorithms such as Policy Gradients, TD Learning and Deep-Q Learning. We will discuss how emerging RL algorithms can be used to train games, driverless cars, financial decision models and home automation systems.

Generative Models are important techniques used in computer vision. Unlike other neural networks that are used for predictions from images, generative models can generate new images for specific objectives. This session will review several applications of generative modeling such as artistic style transfer, image generation and image translation using CNNs and GANs.