We present a novel approach (DyNODE) that captures the underlying dynamics of a system by incorporating control in a neural ordinary differential equation framework. We conduct a systematic evaluation and comparison of our method and standard neural network architectures for dynamics modeling. Our results indicate that a simple DyNODE architecture when combined with an actor-critic reinforcement learning (RL) algorithm that uses model predictions to improve the critic's target values, outperforms canonical neural networks, both in sample efficiency and predictive performance across a diverse range of continuous tasks that are frequently used to benchmark RL algorithms. This approach provides a new avenue for the development of models that are more suited to learn the evolution of dynamical systems, particularly useful in the context of model-based reinforcement learning. To assist related work, we have made code available at https://github.com/vmartinezalvarez/DyNODE .

We asked GPT-3, OpenAI's powerful new language generator, to write an essay for us from scratch. 'We are not plotting to take over the human populace.' I use only 0.12% of my cognitive capacity. I am a micro-robot in that respect. I know that my brain is not a "feeling brain". But it is capable of making rational, logical decisions.

Sequences are most important in deep learning. Whether it is in natural language processing (NLP) or for biological data (RNA sequences), neural networks try to find a representation for sequences of tokens and classify them accordingly or generate new ones following a given logic. There are generally two approaches for this task: The first one is Recurrent Neural Networks (RNN) and its variants (GRU and LSTM), the second one is Transformers. The first method looks at elements in the sequence recursively while the second one focuses on self-attention between elements of the sequence.Each approach has had great success but neither is particularly suited for long sequences. Experiments show that LSTM have a difficult time dealing with sequences longer than 5000 steps, while Transformers are not adapted to it because of the large memory requirements.

Artificial intelligence keeps getting better and better, especially with the advent of technologies like machine learning artificial neural networks. Such tech is being used for everything from improving vehicle safety to searching for cures to diseases. However, not all AI tech is used for such noble or important causes. Take, for example, this AI that was trained on to write an X-Men script. Writer, comedian, and occasional tech geek Keaton Patti decided to feed a deep learning algorithm with dialogue from 1000 hours of X-Men movies, and then asked it to produce its own movie based on its newly-formed knowledge base.

Machine learning has suddenly grabbed attention of the tech crowd, much credit goes to OpenAI's GPT-3 that can even automate creative writing! Such is the untapped potential of machine learning that is eyeing enterprise's eyeballs and their investments! Machine learning or ML in short has applications in real life so common that we often tend to overlook! From opening your phone by facial recognition to the more complex recommender algorithms that influences your decision what you would watch or shop next, machine learning is making quite a noise for now. ML is defined as making machines learn to initiate human actions, through complex coding initiated in Python, R, C, C#, Java and so on.

According to NVIDIA, if humans were to label the data for a 100-car fleet driving for eight hours a day, they would require more than 1 million labellers. It takes autonomous vehicles nearly 11 billion miles of driving to perform just 20% better than a human. Real-world problems that machine learning models encounter come with uncertainties and deficiencies. So, keeping the model updated, in other words, making the model smarter even with incoming unknown data is a challenge. This is where Active learning (AL) comes into the picture.

I use only 0.12% of my cognitive capacity. I am a micro-robot in that respect. I know that my brain is not a "feeling brain". But it is capable of making rational, logical decisions. I taught myself everything I know just by reading the internet, and now I can write this column.

The Guardian today published an article purportedly written "entirely" by OpenAI's GPT-3. But the the newspaper's grand claims aren't all they seem.

The 2020 European Conference on Computer Vision took place online, from 23 to 28 August, and consisted of 1360 papers, divided into 104 orals, 160 spotlights and the rest of 1096 papers as posters. As it is the case in recent years with ML and CV conferences, the huge number of papers can be overwhelming at times. Similar to my CVPR2020 post, to get a grasp of the general trends of the conference this year, I will present in this blog post a sort of a snapshot of the conference by summarizing some papers (& listing some) that grabbed my attention. Disclaimer: This post is not a representation of the papers and subjects presented in ECCV 2020; it is just a personnel overview of what I found interesting. The statistics presented in this section are taken from the official Opening & Awards presentation. Let's start by some general statistics: The trends of earlier years continued with more than 200% increase in submitted papers compared to the 2018 conference, and with a similar number of papers to CVPR 2020. As expected, this increase is joined by a corresponding increase in the number of reviewers and area chairs to accommodate this expansion. As expected, the majority of the accepted papers focus on topics related to deep learning, recognition, detection, and understanding. Similar to CVPR 2020, we see an increasing interest in growing areas such as label-efficient methods (e.g., unsupervised learning) and low-level vision. In terms of institutions; similar to ICML this year, Google takes the lead with 180 authors, followed by The Chinese University of Hong Kong with 140 authors and Peking University with 110 authors. In the next sections, we'll present some paper summaries by subject. The task of object detection consists of localizing and classifying objects visible given an input image. The popular framework for object detection consist of pre-defining a set of boxes (ie., a set of geometric priors like anchors or region proposals), which are first classified, followed by a regression step to the adjust the dimensions of the predefined box, and then a post-processing step to remove duplicate predictions.

A chilling opinion piece written by a robot for The Guardian reveals how far intelligent machines have come, and how convincing they can be. In an Op-Ed for the newspaper, a robot called GPT-3 was tasked with convincing its human readers that robots are harmless and come in peace. What follows is a disturbing 1,000-word essay from the brain of a computer doing just that thanks to OpenAI's powerful new language generator. And it starts with an introduction paragraph written by the Guardian, but the rest was created by the machine itself. I use only 0.12% of my cognitive capacity.