This paper introduces a Modified User Datagram Protocol (UDP) for Federated Learning to ensure efficiency and reliability in the model parameter transport process, maximizing the potential of the Global model in each Federated Learning round. In developing and testing this protocol, the NS3 simulator is utilized to simulate the packet transport over the network and Google TensorFlow is used to create a custom Federated learning environment. In this preliminary implementation, the simulation contains three nodes where two nodes are client nodes, and one is a server node. The results obtained in this paper provide confidence in the capabilities of the protocol in the future of Federated Learning therefore, in future the Modified UDP will be tested on a larger Federated learning system with a TensorFlow model containing more parameters and a comparison between the traditional UDP protocol and the Modified UDP protocol will be simulated. Optimization of the Modified UDP will also be explored to improve efficiency while ensuring reliability.

Spoken language recognition (SLR) refers to the automatic process used to determine the language present in a speech sample. SLR is an important task in its own right, for example, as a tool to analyze or categorize large amounts of multi-lingual data. Further, it is also an essential tool for selecting downstream applications in a work flow, for example, to chose appropriate speech recognition or machine translation models. SLR systems are usually composed of two stages, one where an embedding representing the audio sample is extracted and a second one which computes the final scores for each language. In this work, we approach the SLR task as a detection problem and implement the second stage as a probabilistic linear discriminant analysis (PLDA) model. We show that discriminative training of the PLDA parameters gives large gains with respect to the usual generative training. Further, we propose a novel hierarchical approach where two PLDA models are trained, one to generate scores for clusters of highly-related languages and a second one to generate scores conditional to each cluster. The final language detection scores are computed as a combination of these two sets of scores. The complete model is trained discriminatively to optimize a cross-entropy objective. We show that this hierarchical approach consistently outperforms the non-hierarchical one for detection of highly related languages, in many cases by large margins. We train our systems on a collection of datasets including over 100 languages, and test them both on matched and mismatched conditions, showing that the gains are robust to condition mismatch.

The US Court of Appeals for the Federal Circuit affirmed on August 5 that only a natural person--not an artificial intelligence system--can be an inventor. Artificial Intelligence (AI) technology is widely applied as a tool in different technical areas, such as machine learning, image processing, and speech recognition. More complex AI technology can create new products or processes with little or no human help. If an AI system can independently create something new, can it be designated as an inventor? The Federal Circuit finally settled this issue--affirming decisions of the US Patent and Trademark Office (USPTO) and Eastern District of Virginia that an AI system cannot be an inventor.

"The development of full artificial intelligence could spell the end of the human race…it would take off on its own, and re-design itself at an ever-increasing rate. Humans, who are limited by slow biological evolution, couldn't compete, and would be superseded." Artificial Intelligence is undoubtedly one of the key technologies that defines the 21st century. Before throwing this two-word phrase around, having a general understanding of what Artificial Intelligence (AI) entails is important. To put it simply, AI is an attempt to emulate and simulate varied forms of human intelligence in machines.

The layoffs are part of a restructuring that iRobot said will save the company up to $10 million in 2022 and between $30-$40 million in 2023. This was the same day iRobot announced it was being acquired by Amazon for $1.7 billion. However, iRobot said the two events are not related. To better align costs with near-term revenue, part of the restructuring includes shifting certain non-core engineering functions to lower-cost regions and increasing use of iRobot's joint design manufacturing (JDM) partners. "These actions help support the company's near-term priorities to drive innovation by executing on its product roadmaps, optimize inventory levels across all major channels, expand DTC sales and position the business for profitable growth in 2023," iRobot said in its earnings statement.

BRIAN KENNY: Revolutions often have humble origins, a small group with big ideas gathering to plant seeds of disruption. So, it was in the dog days of summer in 1956, when 10 academics gathered on the campus of Dartmouth College to discuss how to make machines use language and form abstractions and concepts to solve the kinds of problems now reserved for humans. The conference led to the founding of a new field of study, artificial intelligence. Six decades hence, we are in the midst of an AI revolution that is already dramatically changing entire sectors like healthcare, transportation, education, banking, and retail. But AI is not without its critics. Elon Musk famously said that, "With artificial intelligence, we're summoning the demon." While Stephen Hawking believed the development of full artificial intelligence could spell the end of the human race. So, whose job is it to make sure that such a vision never comes to pass? Today on Cold Call, we've invited Professor Tsedal Neeley to discuss her case entitled, "Timnit Gebru: Silenced No More on AI Bias and The Harms of Large Language Models." Tsedal Neeley's work focuses on how leaders can scale their organizations by developing and implementing global and digital strategies.

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position, and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection provides valuable information for multiparallel word alignment. Our method outperforms previous work on three word-alignment datasets and on a downstream task.

Artificial neural networks (ANNs), despite their universal function approximation capability and practical success, are subject to catastrophic forgetting. Catastrophic forgetting refers to the abrupt unlearning of a previous task when a new task is learned. It is an emergent phenomenon that hinders continual learning. Existing universal function approximation theorems for ANNs guarantee function approximation ability, but do not predict catastrophic forgetting. This paper presents a novel universal approximation theorem for multi-variable functions using only single-variable functions and exponential functions. Furthermore, we present ATLAS: a novel ANN architecture based on the new theorem. It is shown that ATLAS is a universal function approximator capable of some memory retention, and continual learning. The memory of ATLAS is imperfect, with some off-target effects during continual learning, but it is well-behaved and predictable. An efficient implementation of ATLAS is provided. Experiments are conducted to evaluate both the function approximation and memory retention capabilities of ATLAS.

Recent work demonstrates a bias in the GPT-3 model towards generating violent text completions when prompted about Muslims, compared with Christians and Hindus. Two pre-registered replication attempts, one exact and one approximate, found only the weakest bias in the more recent Instruct Series version of GPT-3, fine-tuned to eliminate biased and toxic outputs. Few violent completions were observed. Additional pre-registered experiments, however, showed that using common names associated with the religions in prompts yields a highly significant increase in violent completions, also revealing a stronger second-order bias against Muslims. Names of Muslim celebrities from non-violent domains resulted in relatively fewer violent completions, suggesting that access to individualized information can steer the model away from using stereotypes. Nonetheless, content analysis revealed religion-specific violent themes containing highly offensive ideas regardless of prompt format. Our results show the need for additional debiasing of large language models to address higher-order schemas and associations.

Ottonomy.IO has announced the close of their seed funding round of $3.3 million bringing its total funding to date to $4.9M; supporting the scale of Ottobots for fully autonomous airport, retail and restaurant deliveries. The funding round is led by Pi Ventures who back deep tech startups. Connetic Ventures and Branded Hospitality Ventures and the Founder & CEO of Addverb Technologies, Sangeet Kumar, also joined this round; making the group a dynamic mix from retail, food and robotics industry investors for Ottonomy's seed round. "Last mile delivery is the least productive, yet the most expensive part of the delivery chain. There is a strong need for automation, which Ottonomy fulfills with Ottobots," says Roopan Aulakh, Managing Director from pi Ventures.